summaryrefslogtreecommitdiffstats
path: root/Documentation/admin-guide/hw-vuln
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/admin-guide/hw-vuln')
-rw-r--r--Documentation/admin-guide/hw-vuln/gather_data_sampling.rst109
-rw-r--r--Documentation/admin-guide/hw-vuln/index.rst20
-rw-r--r--Documentation/admin-guide/hw-vuln/l1tf.rst615
-rw-r--r--Documentation/admin-guide/hw-vuln/mds.rst311
-rw-r--r--Documentation/admin-guide/hw-vuln/multihit.rst167
-rw-r--r--Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst260
-rw-r--r--Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst149
-rw-r--r--Documentation/admin-guide/hw-vuln/spectre.rst804
-rw-r--r--Documentation/admin-guide/hw-vuln/srso.rst133
-rw-r--r--Documentation/admin-guide/hw-vuln/tsx_async_abort.rst277
10 files changed, 2845 insertions, 0 deletions
diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst
new file mode 100644
index 000000000..264bfa937
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst
@@ -0,0 +1,109 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+GDS - Gather Data Sampling
+==========================
+
+Gather Data Sampling is a hardware vulnerability which allows unprivileged
+speculative access to data which was previously stored in vector registers.
+
+Problem
+-------
+When a gather instruction performs loads from memory, different data elements
+are merged into the destination vector register. However, when a gather
+instruction that is transiently executed encounters a fault, stale data from
+architectural or internal vector registers may get transiently forwarded to the
+destination vector register instead. This will allow a malicious attacker to
+infer stale data using typical side channel techniques like cache timing
+attacks. GDS is a purely sampling-based attack.
+
+The attacker uses gather instructions to infer the stale vector register data.
+The victim does not need to do anything special other than use the vector
+registers. The victim does not need to use gather instructions to be
+vulnerable.
+
+Because the buffers are shared between Hyper-Threads cross Hyper-Thread attacks
+are possible.
+
+Attack scenarios
+----------------
+Without mitigation, GDS can infer stale data across virtually all
+permission boundaries:
+
+ Non-enclaves can infer SGX enclave data
+ Userspace can infer kernel data
+ Guests can infer data from hosts
+ Guest can infer guest from other guests
+ Users can infer data from other users
+
+Because of this, it is important to ensure that the mitigation stays enabled in
+lower-privilege contexts like guests and when running outside SGX enclaves.
+
+The hardware enforces the mitigation for SGX. Likewise, VMMs should ensure
+that guests are not allowed to disable the GDS mitigation. If a host erred and
+allowed this, a guest could theoretically disable GDS mitigation, mount an
+attack, and re-enable it.
+
+Mitigation mechanism
+--------------------
+This issue is mitigated in microcode. The microcode defines the following new
+bits:
+
+ ================================ === ============================
+ IA32_ARCH_CAPABILITIES[GDS_CTRL] R/O Enumerates GDS vulnerability
+ and mitigation support.
+ IA32_ARCH_CAPABILITIES[GDS_NO] R/O Processor is not vulnerable.
+ IA32_MCU_OPT_CTRL[GDS_MITG_DIS] R/W Disables the mitigation
+ 0 by default.
+ IA32_MCU_OPT_CTRL[GDS_MITG_LOCK] R/W Locks GDS_MITG_DIS=0. Writes
+ to GDS_MITG_DIS are ignored
+ Can't be cleared once set.
+ ================================ === ============================
+
+GDS can also be mitigated on systems that don't have updated microcode by
+disabling AVX. This can be done by setting gather_data_sampling="force" or
+"clearcpuid=avx" on the kernel command-line.
+
+If used, these options will disable AVX use by turning off XSAVE YMM support.
+However, the processor will still enumerate AVX support. Userspace that
+does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM
+support will break.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The mitigation can be disabled by setting "gather_data_sampling=off" or
+"mitigations=off" on the kernel command line. Not specifying either will default
+to the mitigation being enabled. Specifying "gather_data_sampling=force" will
+use the microcode mitigation when available or disable AVX on affected systems
+where the microcode hasn't been updated to include the mitigation.
+
+GDS System Information
+------------------------
+The kernel provides vulnerability status information through sysfs. For
+GDS this can be accessed by the following sysfs file:
+
+/sys/devices/system/cpu/vulnerabilities/gather_data_sampling
+
+The possible values contained in this file are:
+
+ ============================== =============================================
+ Not affected Processor not vulnerable.
+ Vulnerable Processor vulnerable and mitigation disabled.
+ Vulnerable: No microcode Processor vulnerable and microcode is missing
+ mitigation.
+ Mitigation: AVX disabled,
+ no microcode Processor is vulnerable and microcode is missing
+ mitigation. AVX disabled as mitigation.
+ Mitigation: Microcode Processor is vulnerable and mitigation is in
+ effect.
+ Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in
+ effect and cannot be disabled.
+ Unknown: Dependent on
+ hypervisor status Running on a virtual guest processor that is
+ affected but with no way to know if host
+ processor is mitigated or vulnerable.
+ ============================== =============================================
+
+GDS Default mitigation
+----------------------
+The updated microcode will enable the mitigation by default. The kernel's
+default action is to leave the mitigation enabled.
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
new file mode 100644
index 000000000..84742be22
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -0,0 +1,20 @@
+========================
+Hardware vulnerabilities
+========================
+
+This section describes CPU vulnerabilities and provides an overview of the
+possible mitigations along with guidance for selecting mitigations if they
+are configurable at compile, boot or run time.
+
+.. toctree::
+ :maxdepth: 1
+
+ spectre
+ l1tf
+ mds
+ tsx_async_abort
+ multihit.rst
+ special-register-buffer-data-sampling.rst
+ processor_mmio_stale_data.rst
+ gather_data_sampling.rst
+ srso
diff --git a/Documentation/admin-guide/hw-vuln/l1tf.rst b/Documentation/admin-guide/hw-vuln/l1tf.rst
new file mode 100644
index 000000000..3eeeb488d
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/l1tf.rst
@@ -0,0 +1,615 @@
+L1TF - L1 Terminal Fault
+========================
+
+L1 Terminal Fault is a hardware vulnerability which allows unprivileged
+speculative access to data which is available in the Level 1 Data Cache
+when the page table entry controlling the virtual address, which is used
+for the access, has the Present bit cleared or other reserved bits set.
+
+Affected processors
+-------------------
+
+This vulnerability affects a wide range of Intel processors. The
+vulnerability is not present on:
+
+ - Processors from AMD, Centaur and other non Intel vendors
+
+ - Older processor models, where the CPU family is < 6
+
+ - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft,
+ Penwell, Pineview, Silvermont, Airmont, Merrifield)
+
+ - The Intel XEON PHI family
+
+ - Intel processors which have the ARCH_CAP_RDCL_NO bit set in the
+ IA32_ARCH_CAPABILITIES MSR. If the bit is set the CPU is not affected
+ by the Meltdown vulnerability either. These CPUs should become
+ available by end of 2018.
+
+Whether a processor is affected or not can be read out from the L1TF
+vulnerability file in sysfs. See :ref:`l1tf_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entries are related to the L1TF vulnerability:
+
+ ============= ================= ==============================
+ CVE-2018-3615 L1 Terminal Fault SGX related aspects
+ CVE-2018-3620 L1 Terminal Fault OS, SMM related aspects
+ CVE-2018-3646 L1 Terminal Fault Virtualization related aspects
+ ============= ================= ==============================
+
+Problem
+-------
+
+If an instruction accesses a virtual address for which the relevant page
+table entry (PTE) has the Present bit cleared or other reserved bits set,
+then speculative execution ignores the invalid PTE and loads the referenced
+data if it is present in the Level 1 Data Cache, as if the page referenced
+by the address bits in the PTE was still present and accessible.
+
+While this is a purely speculative mechanism and the instruction will raise
+a page fault when it is retired eventually, the pure act of loading the
+data and making it available to other speculative instructions opens up the
+opportunity for side channel attacks to unprivileged malicious code,
+similar to the Meltdown attack.
+
+While Meltdown breaks the user space to kernel space protection, L1TF
+allows to attack any physical memory address in the system and the attack
+works across all protection domains. It allows an attack of SGX and also
+works from inside virtual machines because the speculation bypasses the
+extended page table (EPT) protection mechanism.
+
+
+Attack scenarios
+----------------
+
+1. Malicious user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+ Operating Systems store arbitrary information in the address bits of a
+ PTE which is marked non present. This allows a malicious user space
+ application to attack the physical memory to which these PTEs resolve.
+ In some cases user-space can maliciously influence the information
+ encoded in the address bits of the PTE, thus making attacks more
+ deterministic and more practical.
+
+ The Linux kernel contains a mitigation for this attack vector, PTE
+ inversion, which is permanently enabled and has no performance
+ impact. The kernel ensures that the address bits of PTEs, which are not
+ marked present, never point to cacheable physical memory space.
+
+ A system with an up to date kernel is protected against attacks from
+ malicious user space applications.
+
+2. Malicious guest in a virtual machine
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The fact that L1TF breaks all domain protections allows malicious guest
+ OSes, which can control the PTEs directly, and malicious guest user
+ space applications, which run on an unprotected guest kernel lacking the
+ PTE inversion mitigation for L1TF, to attack physical host memory.
+
+ A special aspect of L1TF in the context of virtualization is symmetric
+ multi threading (SMT). The Intel implementation of SMT is called
+ HyperThreading. The fact that Hyperthreads on the affected processors
+ share the L1 Data Cache (L1D) is important for this. As the flaw allows
+ only to attack data which is present in L1D, a malicious guest running
+ on one Hyperthread can attack the data which is brought into the L1D by
+ the context which runs on the sibling Hyperthread of the same physical
+ core. This context can be host OS, host user space or a different guest.
+
+ If the processor does not support Extended Page Tables, the attack is
+ only possible, when the hypervisor does not sanitize the content of the
+ effective (shadow) page tables.
+
+ While solutions exist to mitigate these attack vectors fully, these
+ mitigations are not enabled by default in the Linux kernel because they
+ can affect performance significantly. The kernel provides several
+ mechanisms which can be utilized to address the problem depending on the
+ deployment scenario. The mitigations, their protection scope and impact
+ are described in the next sections.
+
+ The default mitigations and the rationale for choosing them are explained
+ at the end of this document. See :ref:`default_mitigations`.
+
+.. _l1tf_sys_info:
+
+L1TF system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current L1TF
+status of the system: whether the system is vulnerable, and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/l1tf
+
+The possible values in this file are:
+
+ =========================== ===============================
+ 'Not affected' The processor is not vulnerable
+ 'Mitigation: PTE Inversion' The host protection is active
+ =========================== ===============================
+
+If KVM/VMX is enabled and the processor is vulnerable then the following
+information is appended to the 'Mitigation: PTE Inversion' part:
+
+ - SMT status:
+
+ ===================== ================
+ 'VMX: SMT vulnerable' SMT is enabled
+ 'VMX: SMT disabled' SMT is disabled
+ ===================== ================
+
+ - L1D Flush mode:
+
+ ================================ ====================================
+ 'L1D vulnerable' L1D flushing is disabled
+
+ 'L1D conditional cache flushes' L1D flush is conditionally enabled
+
+ 'L1D cache flushes' L1D flush is unconditionally enabled
+ ================================ ====================================
+
+The resulting grade of protection is discussed in the following sections.
+
+
+Host mitigation mechanism
+-------------------------
+
+The kernel is unconditionally protected against L1TF attacks from malicious
+user space running on the host.
+
+
+Guest mitigation mechanisms
+---------------------------
+
+.. _l1d_flush:
+
+1. L1D flush on VMENTER
+^^^^^^^^^^^^^^^^^^^^^^^
+
+ To make sure that a guest cannot attack data which is present in the L1D
+ the hypervisor flushes the L1D before entering the guest.
+
+ Flushing the L1D evicts not only the data which should not be accessed
+ by a potentially malicious guest, it also flushes the guest
+ data. Flushing the L1D has a performance impact as the processor has to
+ bring the flushed guest data back into the L1D. Depending on the
+ frequency of VMEXIT/VMENTER and the type of computations in the guest
+ performance degradation in the range of 1% to 50% has been observed. For
+ scenarios where guest VMEXIT/VMENTER are rare the performance impact is
+ minimal. Virtio and mechanisms like posted interrupts are designed to
+ confine the VMEXITs to a bare minimum, but specific configurations and
+ application scenarios might still suffer from a high VMEXIT rate.
+
+ The kernel provides two L1D flush modes:
+ - conditional ('cond')
+ - unconditional ('always')
+
+ The conditional mode avoids L1D flushing after VMEXITs which execute
+ only audited code paths before the corresponding VMENTER. These code
+ paths have been verified that they cannot expose secrets or other
+ interesting data to an attacker, but they can leak information about the
+ address space layout of the hypervisor.
+
+ Unconditional mode flushes L1D on all VMENTER invocations and provides
+ maximum protection. It has a higher overhead than the conditional
+ mode. The overhead cannot be quantified correctly as it depends on the
+ workload scenario and the resulting number of VMEXITs.
+
+ The general recommendation is to enable L1D flush on VMENTER. The kernel
+ defaults to conditional mode on affected processors.
+
+ **Note**, that L1D flush does not prevent the SMT problem because the
+ sibling thread will also bring back its data into the L1D which makes it
+ attackable again.
+
+ L1D flush can be controlled by the administrator via the kernel command
+ line and sysfs control files. See :ref:`mitigation_control_command_line`
+ and :ref:`mitigation_control_kvm`.
+
+.. _guest_confinement:
+
+2. Guest VCPU confinement to dedicated physical cores
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ To address the SMT problem, it is possible to make a guest or a group of
+ guests affine to one or more physical cores. The proper mechanism for
+ that is to utilize exclusive cpusets to ensure that no other guest or
+ host tasks can run on these cores.
+
+ If only a single guest or related guests run on sibling SMT threads on
+ the same physical core then they can only attack their own memory and
+ restricted parts of the host memory.
+
+ Host memory is attackable, when one of the sibling SMT threads runs in
+ host OS (hypervisor) context and the other in guest context. The amount
+ of valuable information from the host OS context depends on the context
+ which the host OS executes, i.e. interrupts, soft interrupts and kernel
+ threads. The amount of valuable data from these contexts cannot be
+ declared as non-interesting for an attacker without deep inspection of
+ the code.
+
+ **Note**, that assigning guests to a fixed set of physical cores affects
+ the ability of the scheduler to do load balancing and might have
+ negative effects on CPU utilization depending on the hosting
+ scenario. Disabling SMT might be a viable alternative for particular
+ scenarios.
+
+ For further information about confining guests to a single or to a group
+ of cores consult the cpusets documentation:
+
+ https://www.kernel.org/doc/Documentation/admin-guide/cgroup-v1/cpusets.rst
+
+.. _interrupt_isolation:
+
+3. Interrupt affinity
+^^^^^^^^^^^^^^^^^^^^^
+
+ Interrupts can be made affine to logical CPUs. This is not universally
+ true because there are types of interrupts which are truly per CPU
+ interrupts, e.g. the local timer interrupt. Aside of that multi queue
+ devices affine their interrupts to single CPUs or groups of CPUs per
+ queue without allowing the administrator to control the affinities.
+
+ Moving the interrupts, which can be affinity controlled, away from CPUs
+ which run untrusted guests, reduces the attack vector space.
+
+ Whether the interrupts with are affine to CPUs, which run untrusted
+ guests, provide interesting data for an attacker depends on the system
+ configuration and the scenarios which run on the system. While for some
+ of the interrupts it can be assumed that they won't expose interesting
+ information beyond exposing hints about the host OS memory layout, there
+ is no way to make general assumptions.
+
+ Interrupt affinity can be controlled by the administrator via the
+ /proc/irq/$NR/smp_affinity[_list] files. Limited documentation is
+ available at:
+
+ https://www.kernel.org/doc/Documentation/core-api/irq/irq-affinity.rst
+
+.. _smt_control:
+
+4. SMT control
+^^^^^^^^^^^^^^
+
+ To prevent the SMT issues of L1TF it might be necessary to disable SMT
+ completely. Disabling SMT can have a significant performance impact, but
+ the impact depends on the hosting scenario and the type of workloads.
+ The impact of disabling SMT needs also to be weighted against the impact
+ of other mitigation solutions like confining guests to dedicated cores.
+
+ The kernel provides a sysfs interface to retrieve the status of SMT and
+ to control it. It also provides a kernel command line interface to
+ control SMT.
+
+ The kernel command line interface consists of the following options:
+
+ =========== ==========================================================
+ nosmt Affects the bring up of the secondary CPUs during boot. The
+ kernel tries to bring all present CPUs online during the
+ boot process. "nosmt" makes sure that from each physical
+ core only one - the so called primary (hyper) thread is
+ activated. Due to a design flaw of Intel processors related
+ to Machine Check Exceptions the non primary siblings have
+ to be brought up at least partially and are then shut down
+ again. "nosmt" can be undone via the sysfs interface.
+
+ nosmt=force Has the same effect as "nosmt" but it does not allow to
+ undo the SMT disable via the sysfs interface.
+ =========== ==========================================================
+
+ The sysfs interface provides two files:
+
+ - /sys/devices/system/cpu/smt/control
+ - /sys/devices/system/cpu/smt/active
+
+ /sys/devices/system/cpu/smt/control:
+
+ This file allows to read out the SMT control state and provides the
+ ability to disable or (re)enable SMT. The possible states are:
+
+ ============== ===================================================
+ on SMT is supported by the CPU and enabled. All
+ logical CPUs can be onlined and offlined without
+ restrictions.
+
+ off SMT is supported by the CPU and disabled. Only
+ the so called primary SMT threads can be onlined
+ and offlined without restrictions. An attempt to
+ online a non-primary sibling is rejected
+
+ forceoff Same as 'off' but the state cannot be controlled.
+ Attempts to write to the control file are rejected.
+
+ notsupported The processor does not support SMT. It's therefore
+ not affected by the SMT implications of L1TF.
+ Attempts to write to the control file are rejected.
+ ============== ===================================================
+
+ The possible states which can be written into this file to control SMT
+ state are:
+
+ - on
+ - off
+ - forceoff
+
+ /sys/devices/system/cpu/smt/active:
+
+ This file reports whether SMT is enabled and active, i.e. if on any
+ physical core two or more sibling threads are online.
+
+ SMT control is also possible at boot time via the l1tf kernel command
+ line parameter in combination with L1D flush control. See
+ :ref:`mitigation_control_command_line`.
+
+5. Disabling EPT
+^^^^^^^^^^^^^^^^
+
+ Disabling EPT for virtual machines provides full mitigation for L1TF even
+ with SMT enabled, because the effective page tables for guests are
+ managed and sanitized by the hypervisor. Though disabling EPT has a
+ significant performance impact especially when the Meltdown mitigation
+ KPTI is enabled.
+
+ EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+There is ongoing research and development for new mitigation mechanisms to
+address the performance impact of disabling SMT or EPT.
+
+.. _mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the L1TF mitigations at boot
+time with the option "l1tf=". The valid arguments for this option are:
+
+ ============ =============================================================
+ full Provides all available mitigations for the L1TF
+ vulnerability. Disables SMT and enables all mitigations in
+ the hypervisors, i.e. unconditional L1D flushing
+
+ SMT control and L1D flush control via the sysfs interface
+ is still possible after boot. Hypervisors will issue a
+ warning when the first VM is started in a potentially
+ insecure configuration, i.e. SMT enabled or L1D flush
+ disabled.
+
+ full,force Same as 'full', but disables SMT and L1D flush runtime
+ control. Implies the 'nosmt=force' command line option.
+ (i.e. sysfs control of SMT is disabled.)
+
+ flush Leaves SMT enabled and enables the default hypervisor
+ mitigation, i.e. conditional L1D flushing
+
+ SMT control and L1D flush control via the sysfs interface
+ is still possible after boot. Hypervisors will issue a
+ warning when the first VM is started in a potentially
+ insecure configuration, i.e. SMT enabled or L1D flush
+ disabled.
+
+ flush,nosmt Disables SMT and enables the default hypervisor mitigation,
+ i.e. conditional L1D flushing.
+
+ SMT control and L1D flush control via the sysfs interface
+ is still possible after boot. Hypervisors will issue a
+ warning when the first VM is started in a potentially
+ insecure configuration, i.e. SMT enabled or L1D flush
+ disabled.
+
+ flush,nowarn Same as 'flush', but hypervisors will not warn when a VM is
+ started in a potentially insecure configuration.
+
+ off Disables hypervisor mitigations and doesn't emit any
+ warnings.
+ It also drops the swap size and available RAM limit restrictions
+ on both hypervisor and bare metal.
+
+ ============ =============================================================
+
+The default is 'flush'. For details about L1D flushing see :ref:`l1d_flush`.
+
+
+.. _mitigation_control_kvm:
+
+Mitigation control for KVM - module parameter
+-------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism, flushing the L1D cache when
+entering a guest, can be controlled with a module parameter.
+
+The option/parameter is "kvm-intel.vmentry_l1d_flush=". It takes the
+following arguments:
+
+ ============ ==============================================================
+ always L1D cache flush on every VMENTER.
+
+ cond Flush L1D on VMENTER only when the code between VMEXIT and
+ VMENTER can leak host memory which is considered
+ interesting for an attacker. This still can leak host memory
+ which allows e.g. to determine the hosts address space layout.
+
+ never Disables the mitigation
+ ============ ==============================================================
+
+The parameter can be provided on the kernel command line, as a module
+parameter when loading the modules and at runtime modified via the sysfs
+file:
+
+/sys/module/kvm_intel/parameters/vmentry_l1d_flush
+
+The default is 'cond'. If 'l1tf=full,force' is given on the kernel command
+line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush
+module parameter is ignored and writes to the sysfs file are rejected.
+
+.. _mitigation_selection:
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The system is protected by the kernel unconditionally and no further
+ action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ If the guest comes from a trusted source and the guest OS kernel is
+ guaranteed to have the L1TF mitigations in place the system is fully
+ protected against L1TF and no further action is required.
+
+ To avoid the overhead of the default L1D flushing on VMENTER the
+ administrator can disable the flushing via the kernel command line and
+ sysfs control files. See :ref:`mitigation_control_command_line` and
+ :ref:`mitigation_control_kvm`.
+
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+3.1. SMT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+ If SMT is not supported by the processor or disabled in the BIOS or by
+ the kernel, it's only required to enforce L1D flushing on VMENTER.
+
+ Conditional L1D flushing is the default behaviour and can be tuned. See
+ :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+3.2. EPT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+ If EPT is not supported by the processor or disabled in the hypervisor,
+ the system is fully protected. SMT can stay enabled and L1D flushing on
+ VMENTER is not required.
+
+ EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+3.3. SMT and EPT supported and active
+"""""""""""""""""""""""""""""""""""""
+
+ If SMT and EPT are supported and active then various degrees of
+ mitigations can be employed:
+
+ - L1D flushing on VMENTER:
+
+ L1D flushing on VMENTER is the minimal protection requirement, but it
+ is only potent in combination with other mitigation methods.
+
+ Conditional L1D flushing is the default behaviour and can be tuned. See
+ :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+ - Guest confinement:
+
+ Confinement of guests to a single or a group of physical cores which
+ are not running any other processes, can reduce the attack surface
+ significantly, but interrupts, soft interrupts and kernel threads can
+ still expose valuable data to a potential attacker. See
+ :ref:`guest_confinement`.
+
+ - Interrupt isolation:
+
+ Isolating the guest CPUs from interrupts can reduce the attack surface
+ further, but still allows a malicious guest to explore a limited amount
+ of host physical memory. This can at least be used to gain knowledge
+ about the host address space layout. The interrupts which have a fixed
+ affinity to the CPUs which run the untrusted guests can depending on
+ the scenario still trigger soft interrupts and schedule kernel threads
+ which might expose valuable information. See
+ :ref:`interrupt_isolation`.
+
+The above three mitigation methods combined can provide protection to a
+certain degree, but the risk of the remaining attack surface has to be
+carefully analyzed. For full protection the following methods are
+available:
+
+ - Disabling SMT:
+
+ Disabling SMT and enforcing the L1D flushing provides the maximum
+ amount of protection. This mitigation is not depending on any of the
+ above mitigation methods.
+
+ SMT control and L1D flushing can be tuned by the command line
+ parameters 'nosmt', 'l1tf', 'kvm-intel.vmentry_l1d_flush' and at run
+ time with the matching sysfs control files. See :ref:`smt_control`,
+ :ref:`mitigation_control_command_line` and
+ :ref:`mitigation_control_kvm`.
+
+ - Disabling EPT:
+
+ Disabling EPT provides the maximum amount of protection as well. It is
+ not depending on any of the above mitigation methods. SMT can stay
+ enabled and L1D flushing is not required, but the performance impact is
+ significant.
+
+ EPT can be disabled in the hypervisor via the 'kvm-intel.ept'
+ parameter.
+
+3.4. Nested virtual machines
+""""""""""""""""""""""""""""
+
+When nested virtualization is in use, three operating systems are involved:
+the bare metal hypervisor, the nested hypervisor and the nested virtual
+machine. VMENTER operations from the nested hypervisor into the nested
+guest will always be processed by the bare metal hypervisor. If KVM is the
+bare metal hypervisor it will:
+
+ - Flush the L1D cache on every switch from the nested hypervisor to the
+ nested virtual machine, so that the nested hypervisor's secrets are not
+ exposed to the nested virtual machine;
+
+ - Flush the L1D cache on every switch from the nested virtual machine to
+ the nested hypervisor; this is a complex operation, and flushing the L1D
+ cache avoids that the bare metal hypervisor's secrets are exposed to the
+ nested virtual machine;
+
+ - Instruct the nested hypervisor to not perform any L1D cache flush. This
+ is an optimization to avoid double L1D flushing.
+
+
+.. _default_mitigations:
+
+Default mitigations
+-------------------
+
+ The kernel default mitigations for vulnerable processors are:
+
+ - PTE inversion to protect against malicious user space. This is done
+ unconditionally and cannot be controlled. The swap storage is limited
+ to ~16TB.
+
+ - L1D conditional flushing on VMENTER when EPT is enabled for
+ a guest.
+
+ The kernel does not by default enforce the disabling of SMT, which leaves
+ SMT systems vulnerable when running untrusted guests with EPT enabled.
+
+ The rationale for this choice is:
+
+ - Force disabling SMT can break existing setups, especially with
+ unattended updates.
+
+ - If regular users run untrusted guests on their machine, then L1TF is
+ just an add on to other malware which might be embedded in an untrusted
+ guest, e.g. spam-bots or attacks on the local network.
+
+ There is no technical way to prevent a user from running untrusted code
+ on their machines blindly.
+
+ - It's technically extremely unlikely and from today's knowledge even
+ impossible that L1TF can be exploited via the most popular attack
+ mechanisms like JavaScript because these mechanisms have no way to
+ control PTEs. If this would be possible and not other mitigation would
+ be possible, then the default might be different.
+
+ - The administrators of cloud and hosting setups have to carefully
+ analyze the risk for their scenarios and make the appropriate
+ mitigation choices, which might even vary across their deployed
+ machines and also result in other changes of their overall setup.
+ There is no way for the kernel to provide a sensible default for this
+ kind of scenarios.
diff --git a/Documentation/admin-guide/hw-vuln/mds.rst b/Documentation/admin-guide/hw-vuln/mds.rst
new file mode 100644
index 000000000..2d19c9f4c
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/mds.rst
@@ -0,0 +1,311 @@
+MDS - Microarchitectural Data Sampling
+======================================
+
+Microarchitectural Data Sampling is a hardware vulnerability which allows
+unprivileged speculative access to data which is available in various CPU
+internal buffers.
+
+Affected processors
+-------------------
+
+This vulnerability affects a wide range of Intel processors. The
+vulnerability is not present on:
+
+ - Processors from AMD, Centaur and other non Intel vendors
+
+ - Older processor models, where the CPU family is < 6
+
+ - Some Atoms (Bonnell, Saltwell, Goldmont, GoldmontPlus)
+
+ - Intel processors which have the ARCH_CAP_MDS_NO bit set in the
+ IA32_ARCH_CAPABILITIES MSR.
+
+Whether a processor is affected or not can be read out from the MDS
+vulnerability file in sysfs. See :ref:`mds_sys_info`.
+
+Not all processors are affected by all variants of MDS, but the mitigation
+is identical for all of them so the kernel treats them as a single
+vulnerability.
+
+Related CVEs
+------------
+
+The following CVE entries are related to the MDS vulnerability:
+
+ ============== ===== ===================================================
+ CVE-2018-12126 MSBDS Microarchitectural Store Buffer Data Sampling
+ CVE-2018-12130 MFBDS Microarchitectural Fill Buffer Data Sampling
+ CVE-2018-12127 MLPDS Microarchitectural Load Port Data Sampling
+ CVE-2019-11091 MDSUM Microarchitectural Data Sampling Uncacheable Memory
+ ============== ===== ===================================================
+
+Problem
+-------
+
+When performing store, load, L1 refill operations, processors write data
+into temporary microarchitectural structures (buffers). The data in the
+buffer can be forwarded to load operations as an optimization.
+
+Under certain conditions, usually a fault/assist caused by a load
+operation, data unrelated to the load memory address can be speculatively
+forwarded from the buffers. Because the load operation causes a fault or
+assist and its result will be discarded, the forwarded data will not cause
+incorrect program execution or state changes. But a malicious operation
+may be able to forward this speculative data to a disclosure gadget which
+allows in turn to infer the value via a cache side channel attack.
+
+Because the buffers are potentially shared between Hyper-Threads cross
+Hyper-Thread attacks are possible.
+
+Deeper technical information is available in the MDS specific x86
+architecture section: :ref:`Documentation/x86/mds.rst <mds>`.
+
+
+Attack scenarios
+----------------
+
+Attacks against the MDS vulnerabilities can be mounted from malicious non
+priviledged user space applications running on hosts or guest. Malicious
+guest OSes can obviously mount attacks as well.
+
+Contrary to other speculation based vulnerabilities the MDS vulnerability
+does not allow the attacker to control the memory target address. As a
+consequence the attacks are purely sampling based, but as demonstrated with
+the TLBleed attack samples can be postprocessed successfully.
+
+Web-Browsers
+^^^^^^^^^^^^
+
+ It's unclear whether attacks through Web-Browsers are possible at
+ all. The exploitation through Java-Script is considered very unlikely,
+ but other widely used web technologies like Webassembly could possibly be
+ abused.
+
+
+.. _mds_sys_info:
+
+MDS system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current MDS
+status of the system: whether the system is vulnerable, and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/mds
+
+The possible values in this file are:
+
+ .. list-table::
+
+ * - 'Not affected'
+ - The processor is not vulnerable
+ * - 'Vulnerable'
+ - The processor is vulnerable, but no mitigation enabled
+ * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+ - The processor is vulnerable but microcode is not updated.
+
+ The mitigation is enabled on a best effort basis. See :ref:`vmwerv`
+ * - 'Mitigation: Clear CPU buffers'
+ - The processor is vulnerable and the CPU buffer clearing mitigation is
+ enabled.
+
+If the processor is vulnerable then the following information is appended
+to the above information:
+
+ ======================== ============================================
+ 'SMT vulnerable' SMT is enabled
+ 'SMT mitigated' SMT is enabled and mitigated
+ 'SMT disabled' SMT is disabled
+ 'SMT Host state unknown' Kernel runs in a VM, Host SMT state unknown
+ ======================== ============================================
+
+.. _vmwerv:
+
+Best effort mitigation mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ If the processor is vulnerable, but the availability of the microcode based
+ mitigation mechanism is not advertised via CPUID the kernel selects a best
+ effort mitigation mode. This mode invokes the mitigation instructions
+ without a guarantee that they clear the CPU buffers.
+
+ This is done to address virtualization scenarios where the host has the
+ microcode update applied, but the hypervisor is not yet updated to expose
+ the CPUID to the guest. If the host has updated microcode the protection
+ takes effect otherwise a few cpu cycles are wasted pointlessly.
+
+ The state in the mds sysfs file reflects this situation accordingly.
+
+
+Mitigation mechanism
+-------------------------
+
+The kernel detects the affected CPUs and the presence of the microcode
+which is required.
+
+If a CPU is affected and the microcode is available, then the kernel
+enables the mitigation by default. The mitigation can be controlled at boot
+time via a kernel command line option. See
+:ref:`mds_mitigation_control_command_line`.
+
+.. _cpu_buffer_clear:
+
+CPU buffer clearing
+^^^^^^^^^^^^^^^^^^^
+
+ The mitigation for MDS clears the affected CPU buffers on return to user
+ space and when entering a guest.
+
+ If SMT is enabled it also clears the buffers on idle entry when the CPU
+ is only affected by MSBDS and not any other MDS variant, because the
+ other variants cannot be protected against cross Hyper-Thread attacks.
+
+ For CPUs which are only affected by MSBDS the user space, guest and idle
+ transition mitigations are sufficient and SMT is not affected.
+
+.. _virt_mechanism:
+
+Virtualization mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The protection for host to guest transition depends on the L1TF
+ vulnerability of the CPU:
+
+ - CPU is affected by L1TF:
+
+ If the L1D flush mitigation is enabled and up to date microcode is
+ available, the L1D flush mitigation is automatically protecting the
+ guest transition.
+
+ If the L1D flush mitigation is disabled then the MDS mitigation is
+ invoked explicit when the host MDS mitigation is enabled.
+
+ For details on L1TF and virtualization see:
+ :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <mitigation_control_kvm>`.
+
+ - CPU is not affected by L1TF:
+
+ CPU buffers are flushed before entering the guest when the host MDS
+ mitigation is enabled.
+
+ The resulting MDS protection matrix for the host to guest transition:
+
+ ============ ===== ============= ============ =================
+ L1TF MDS VMX-L1FLUSH Host MDS MDS-State
+
+ Don't care No Don't care N/A Not affected
+
+ Yes Yes Disabled Off Vulnerable
+
+ Yes Yes Disabled Full Mitigated
+
+ Yes Yes Enabled Don't care Mitigated
+
+ No Yes N/A Off Vulnerable
+
+ No Yes N/A Full Mitigated
+ ============ ===== ============= ============ =================
+
+ This only covers the host to guest transition, i.e. prevents leakage from
+ host to guest, but does not protect the guest internally. Guests need to
+ have their own protections.
+
+.. _xeon_phi:
+
+XEON PHI specific considerations
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The XEON PHI processor family is affected by MSBDS which can be exploited
+ cross Hyper-Threads when entering idle states. Some XEON PHI variants allow
+ to use MWAIT in user space (Ring 3) which opens an potential attack vector
+ for malicious user space. The exposure can be disabled on the kernel
+ command line with the 'ring3mwait=disable' command line option.
+
+ XEON PHI is not affected by the other MDS variants and MSBDS is mitigated
+ before the CPU enters a idle state. As XEON PHI is not affected by L1TF
+ either disabling SMT is not required for full protection.
+
+.. _mds_smt_control:
+
+SMT control
+^^^^^^^^^^^
+
+ All MDS variants except MSBDS can be attacked cross Hyper-Threads. That
+ means on CPUs which are affected by MFBDS or MLPDS it is necessary to
+ disable SMT for full protection. These are most of the affected CPUs; the
+ exception is XEON PHI, see :ref:`xeon_phi`.
+
+ Disabling SMT can have a significant performance impact, but the impact
+ depends on the type of workloads.
+
+ See the relevant chapter in the L1TF mitigation documentation for details:
+ :ref:`Documentation/admin-guide/hw-vuln/l1tf.rst <smt_control>`.
+
+
+.. _mds_mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the MDS mitigations at boot
+time with the option "mds=". The valid arguments for this option are:
+
+ ============ =============================================================
+ full If the CPU is vulnerable, enable all available mitigations
+ for the MDS vulnerability, CPU buffer clearing on exit to
+ userspace and when entering a VM. Idle transitions are
+ protected as well if SMT is enabled.
+
+ It does not automatically disable SMT.
+
+ full,nosmt The same as mds=full, with SMT disabled on vulnerable
+ CPUs. This is the complete mitigation.
+
+ off Disables MDS mitigations completely.
+
+ ============ =============================================================
+
+Not specifying this option is equivalent to "mds=full". For processors
+that are affected by both TAA (TSX Asynchronous Abort) and MDS,
+specifying just "mds=off" without an accompanying "tsx_async_abort=off"
+will have no effect as the same mitigation is used for both
+vulnerabilities.
+
+Mitigation selection guide
+--------------------------
+
+1. Trusted userspace
+^^^^^^^^^^^^^^^^^^^^
+
+ If all userspace applications are from a trusted source and do not
+ execute untrusted code which is supplied externally, then the mitigation
+ can be disabled.
+
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The same considerations as above versus trusted user space apply.
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The protection depends on the state of the L1TF mitigations.
+ See :ref:`virt_mechanism`.
+
+ If the MDS mitigation is enabled and SMT is disabled, guest to host and
+ guest to guest attacks are prevented.
+
+.. _mds_default_mitigations:
+
+Default mitigations
+-------------------
+
+ The kernel default mitigations for vulnerable processors are:
+
+ - Enable CPU buffer clearing
+
+ The kernel does not by default enforce the disabling of SMT, which leaves
+ SMT systems vulnerable when running untrusted code. The same rationale as
+ for L1TF applies.
+ See :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <default_mitigations>`.
diff --git a/Documentation/admin-guide/hw-vuln/multihit.rst b/Documentation/admin-guide/hw-vuln/multihit.rst
new file mode 100644
index 000000000..140e4cec3
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/multihit.rst
@@ -0,0 +1,167 @@
+iTLB multihit
+=============
+
+iTLB multihit is an erratum where some processors may incur a machine check
+error, possibly resulting in an unrecoverable CPU lockup, when an
+instruction fetch hits multiple entries in the instruction TLB. This can
+occur when the page size is changed along with either the physical address
+or cache type. A malicious guest running on a virtualized system can
+exploit this erratum to perform a denial of service attack.
+
+
+Affected processors
+-------------------
+
+Variations of this erratum are present on most Intel Core and Xeon processor
+models. The erratum is not present on:
+
+ - non-Intel processors
+
+ - Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont)
+
+ - Intel processors that have the PSCHANGE_MC_NO bit set in the
+ IA32_ARCH_CAPABILITIES MSR.
+
+
+Related CVEs
+------------
+
+The following CVE entry is related to this issue:
+
+ ============== =================================================
+ CVE-2018-12207 Machine Check Error Avoidance on Page Size Change
+ ============== =================================================
+
+
+Problem
+-------
+
+Privileged software, including OS and virtual machine managers (VMM), are in
+charge of memory management. A key component in memory management is the control
+of the page tables. Modern processors use virtual memory, a technique that creates
+the illusion of a very large memory for processors. This virtual space is split
+into pages of a given size. Page tables translate virtual addresses to physical
+addresses.
+
+To reduce latency when performing a virtual to physical address translation,
+processors include a structure, called TLB, that caches recent translations.
+There are separate TLBs for instruction (iTLB) and data (dTLB).
+
+Under this errata, instructions are fetched from a linear address translated
+using a 4 KB translation cached in the iTLB. Privileged software modifies the
+paging structure so that the same linear address using large page size (2 MB, 4
+MB, 1 GB) with a different physical address or memory type. After the page
+structure modification but before the software invalidates any iTLB entries for
+the linear address, a code fetch that happens on the same linear address may
+cause a machine-check error which can result in a system hang or shutdown.
+
+
+Attack scenarios
+----------------
+
+Attacks against the iTLB multihit erratum can be mounted from malicious
+guests in a virtualized system.
+
+
+iTLB multihit system information
+--------------------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current iTLB
+multihit status of the system:whether the system is vulnerable and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/itlb_multihit
+
+The possible values in this file are:
+
+.. list-table::
+
+ * - Not affected
+ - The processor is not vulnerable.
+ * - KVM: Mitigation: Split huge pages
+ - Software changes mitigate this issue.
+ * - KVM: Mitigation: VMX unsupported
+ - KVM is not vulnerable because Virtual Machine Extensions (VMX) is not supported.
+ * - KVM: Mitigation: VMX disabled
+ - KVM is not vulnerable because Virtual Machine Extensions (VMX) is disabled.
+ * - KVM: Vulnerable
+ - The processor is vulnerable, but no mitigation enabled
+
+
+Enumeration of the erratum
+--------------------------------
+
+A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr
+and will be set on CPU's which are mitigated against this issue.
+
+ ======================================= =========== ===============================
+ IA32_ARCH_CAPABILITIES MSR Not present Possibly vulnerable,check model
+ IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '0' Likely vulnerable,check model
+ IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '1' Not vulnerable
+ ======================================= =========== ===============================
+
+
+Mitigation mechanism
+-------------------------
+
+This erratum can be mitigated by restricting the use of large page sizes to
+non-executable pages. This forces all iTLB entries to be 4K, and removes
+the possibility of multiple hits.
+
+In order to mitigate the vulnerability, KVM initially marks all huge pages
+as non-executable. If the guest attempts to execute in one of those pages,
+the page is broken down into 4K pages, which are then marked executable.
+
+If EPT is disabled or not available on the host, KVM is in control of TLB
+flushes and the problematic situation cannot happen. However, the shadow
+EPT paging mechanism used by nested virtualization is vulnerable, because
+the nested guest can trigger multiple iTLB hits by modifying its own
+(non-nested) page tables. For simplicity, KVM will make large pages
+non-executable in all shadow paging modes.
+
+Mitigation control on the kernel command line and KVM - module parameter
+------------------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism for marking huge pages as
+non-executable can be controlled with a module parameter "nx_huge_pages=".
+The kernel command line allows to control the iTLB multihit mitigations at
+boot time with the option "kvm.nx_huge_pages=".
+
+The valid arguments for these options are:
+
+ ========== ================================================================
+ force Mitigation is enabled. In this case, the mitigation implements
+ non-executable huge pages in Linux kernel KVM module. All huge
+ pages in the EPT are marked as non-executable.
+ If a guest attempts to execute in one of those pages, the page is
+ broken down into 4K pages, which are then marked executable.
+
+ off Mitigation is disabled.
+
+ auto Enable mitigation only if the platform is affected and the kernel
+ was not booted with the "mitigations=off" command line parameter.
+ This is the default option.
+ ========== ================================================================
+
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The system is protected by the kernel unconditionally and no further
+ action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ If the guest comes from a trusted source, you may assume that the guest will
+ not attempt to maliciously exploit these errata and no further action is
+ required.
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ If the guest comes from an untrusted source, the guest host kernel will need
+ to apply iTLB multihit mitigation via the kernel command line or kvm
+ module parameter.
diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
new file mode 100644
index 000000000..c98fd1190
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
@@ -0,0 +1,260 @@
+=========================================
+Processor MMIO Stale Data Vulnerabilities
+=========================================
+
+Processor MMIO Stale Data Vulnerabilities are a class of memory-mapped I/O
+(MMIO) vulnerabilities that can expose data. The sequences of operations for
+exposing data range from simple to very complex. Because most of the
+vulnerabilities require the attacker to have access to MMIO, many environments
+are not affected. System environments using virtualization where MMIO access is
+provided to untrusted guests may need mitigation. These vulnerabilities are
+not transient execution attacks. However, these vulnerabilities may propagate
+stale data into core fill buffers where the data can subsequently be inferred
+by an unmitigated transient execution attack. Mitigation for these
+vulnerabilities includes a combination of microcode update and software
+changes, depending on the platform and usage model. Some of these mitigations
+are similar to those used to mitigate Microarchitectural Data Sampling (MDS) or
+those used to mitigate Special Register Buffer Data Sampling (SRBDS).
+
+Data Propagators
+================
+Propagators are operations that result in stale data being copied or moved from
+one microarchitectural buffer or register to another. Processor MMIO Stale Data
+Vulnerabilities are operations that may result in stale data being directly
+read into an architectural, software-visible state or sampled from a buffer or
+register.
+
+Fill Buffer Stale Data Propagator (FBSDP)
+-----------------------------------------
+Stale data may propagate from fill buffers (FB) into the non-coherent portion
+of the uncore on some non-coherent writes. Fill buffer propagation by itself
+does not make stale data architecturally visible. Stale data must be propagated
+to a location where it is subject to reading or sampling.
+
+Sideband Stale Data Propagator (SSDP)
+-------------------------------------
+The sideband stale data propagator (SSDP) is limited to the client (including
+Intel Xeon server E3) uncore implementation. The sideband response buffer is
+shared by all client cores. For non-coherent reads that go to sideband
+destinations, the uncore logic returns 64 bytes of data to the core, including
+both requested data and unrequested stale data, from a transaction buffer and
+the sideband response buffer. As a result, stale data from the sideband
+response and transaction buffers may now reside in a core fill buffer.
+
+Primary Stale Data Propagator (PSDP)
+------------------------------------
+The primary stale data propagator (PSDP) is limited to the client (including
+Intel Xeon server E3) uncore implementation. Similar to the sideband response
+buffer, the primary response buffer is shared by all client cores. For some
+processors, MMIO primary reads will return 64 bytes of data to the core fill
+buffer including both requested data and unrequested stale data. This is
+similar to the sideband stale data propagator.
+
+Vulnerabilities
+===============
+Device Register Partial Write (DRPW) (CVE-2022-21166)
+-----------------------------------------------------
+Some endpoint MMIO registers incorrectly handle writes that are smaller than
+the register size. Instead of aborting the write or only copying the correct
+subset of bytes (for example, 2 bytes for a 2-byte write), more bytes than
+specified by the write transaction may be written to the register. On
+processors affected by FBSDP, this may expose stale data from the fill buffers
+of the core that created the write transaction.
+
+Shared Buffers Data Sampling (SBDS) (CVE-2022-21125)
+----------------------------------------------------
+After propagators may have moved data around the uncore and copied stale data
+into client core fill buffers, processors affected by MFBDS can leak data from
+the fill buffer. It is limited to the client (including Intel Xeon server E3)
+uncore implementation.
+
+Shared Buffers Data Read (SBDR) (CVE-2022-21123)
+------------------------------------------------
+It is similar to Shared Buffer Data Sampling (SBDS) except that the data is
+directly read into the architectural software-visible state. It is limited to
+the client (including Intel Xeon server E3) uncore implementation.
+
+Affected Processors
+===================
+Not all the CPUs are affected by all the variants. For instance, most
+processors for the server market (excluding Intel Xeon E3 processors) are
+impacted by only Device Register Partial Write (DRPW).
+
+Below is the list of affected Intel processors [#f1]_:
+
+ =================== ============ =========
+ Common name Family_Model Steppings
+ =================== ============ =========
+ HASWELL_X 06_3FH 2,4
+ SKYLAKE_L 06_4EH 3
+ BROADWELL_X 06_4FH All
+ SKYLAKE_X 06_55H 3,4,6,7,11
+ BROADWELL_D 06_56H 3,4,5
+ SKYLAKE 06_5EH 3
+ ICELAKE_X 06_6AH 4,5,6
+ ICELAKE_D 06_6CH 1
+ ICELAKE_L 06_7EH 5
+ ATOM_TREMONT_D 06_86H All
+ LAKEFIELD 06_8AH 1
+ KABYLAKE_L 06_8EH 9 to 12
+ ATOM_TREMONT 06_96H 1
+ ATOM_TREMONT_L 06_9CH 0
+ KABYLAKE 06_9EH 9 to 13
+ COMETLAKE 06_A5H 2,3,5
+ COMETLAKE_L 06_A6H 0,1
+ ROCKETLAKE 06_A7H 1
+ =================== ============ =========
+
+If a CPU is in the affected processor list, but not affected by a variant, it
+is indicated by new bits in MSR IA32_ARCH_CAPABILITIES. As described in a later
+section, mitigation largely remains the same for all the variants, i.e. to
+clear the CPU fill buffers via VERW instruction.
+
+New bits in MSRs
+================
+Newer processors and microcode update on existing affected processors added new
+bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate
+specific variants of Processor MMIO Stale Data vulnerabilities and mitigation
+capability.
+
+MSR IA32_ARCH_CAPABILITIES
+--------------------------
+Bit 13 - SBDR_SSDP_NO - When set, processor is not affected by either the
+ Shared Buffers Data Read (SBDR) vulnerability or the sideband stale
+ data propagator (SSDP).
+Bit 14 - FBSDP_NO - When set, processor is not affected by the Fill Buffer
+ Stale Data Propagator (FBSDP).
+Bit 15 - PSDP_NO - When set, processor is not affected by Primary Stale Data
+ Propagator (PSDP).
+Bit 17 - FB_CLEAR - When set, VERW instruction will overwrite CPU fill buffer
+ values as part of MD_CLEAR operations. Processors that do not
+ enumerate MDS_NO (meaning they are affected by MDS) but that do
+ enumerate support for both L1D_FLUSH and MD_CLEAR implicitly enumerate
+ FB_CLEAR as part of their MD_CLEAR support.
+Bit 18 - FB_CLEAR_CTRL - Processor supports read and write to MSR
+ IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]. On such processors, the FB_CLEAR_DIS
+ bit can be set to cause the VERW instruction to not perform the
+ FB_CLEAR action. Not all processors that support FB_CLEAR will support
+ FB_CLEAR_CTRL.
+
+MSR IA32_MCU_OPT_CTRL
+---------------------
+Bit 3 - FB_CLEAR_DIS - When set, VERW instruction does not perform the FB_CLEAR
+action. This may be useful to reduce the performance impact of FB_CLEAR in
+cases where system software deems it warranted (for example, when performance
+is more critical, or the untrusted software has no MMIO access). Note that
+FB_CLEAR_DIS has no impact on enumeration (for example, it does not change
+FB_CLEAR or MD_CLEAR enumeration) and it may not be supported on all processors
+that enumerate FB_CLEAR.
+
+Mitigation
+==========
+Like MDS, all variants of Processor MMIO Stale Data vulnerabilities have the
+same mitigation strategy to force the CPU to clear the affected buffers before
+an attacker can extract the secrets.
+
+This is achieved by using the otherwise unused and obsolete VERW instruction in
+combination with a microcode update. The microcode clears the affected CPU
+buffers when the VERW instruction is executed.
+
+Kernel reuses the MDS function to invoke the buffer clearing:
+
+ mds_clear_cpu_buffers()
+
+On MDS affected CPUs, the kernel already invokes CPU buffer clear on
+kernel/userspace, hypervisor/guest and C-state (idle) transitions. No
+additional mitigation is needed on such CPUs.
+
+For CPUs not affected by MDS or TAA, mitigation is needed only for the attacker
+with MMIO capability. Therefore, VERW is not required for kernel/userspace. For
+virtualization case, VERW is only needed at VMENTER for a guest with MMIO
+capability.
+
+Mitigation points
+-----------------
+Return to user space
+^^^^^^^^^^^^^^^^^^^^
+Same mitigation as MDS when affected by MDS/TAA, otherwise no mitigation
+needed.
+
+C-State transition
+^^^^^^^^^^^^^^^^^^
+Control register writes by CPU during C-state transition can propagate data
+from fill buffer to uncore buffers. Execute VERW before C-state transition to
+clear CPU fill buffers.
+
+Guest entry point
+^^^^^^^^^^^^^^^^^
+Same mitigation as MDS when processor is also affected by MDS/TAA, otherwise
+execute VERW at VMENTER only for MMIO capable guests. On CPUs not affected by
+MDS/TAA, guest without MMIO access cannot extract secrets using Processor MMIO
+Stale Data vulnerabilities, so there is no need to execute VERW for such guests.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows to control the Processor MMIO Stale Data
+mitigations at boot time with the option "mmio_stale_data=". The valid
+arguments for this option are:
+
+ ========== =================================================================
+ full If the CPU is vulnerable, enable mitigation; CPU buffer clearing
+ on exit to userspace and when entering a VM. Idle transitions are
+ protected as well. It does not automatically disable SMT.
+ full,nosmt Same as full, with SMT disabled on vulnerable CPUs. This is the
+ complete mitigation.
+ off Disables mitigation completely.
+ ========== =================================================================
+
+If the CPU is affected and mmio_stale_data=off is not supplied on the kernel
+command line, then the kernel selects the appropriate mitigation.
+
+Mitigation status information
+-----------------------------
+The Linux kernel provides a sysfs interface to enumerate the current
+vulnerability status of the system: whether the system is vulnerable, and
+which mitigations are active. The relevant sysfs file is:
+
+ /sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+
+The possible values in this file are:
+
+ .. list-table::
+
+ * - 'Not affected'
+ - The processor is not vulnerable
+ * - 'Vulnerable'
+ - The processor is vulnerable, but no mitigation enabled
+ * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+ - The processor is vulnerable, but microcode is not updated. The
+ mitigation is enabled on a best effort basis.
+ * - 'Mitigation: Clear CPU buffers'
+ - The processor is vulnerable and the CPU buffer clearing mitigation is
+ enabled.
+ * - 'Unknown: No mitigations'
+ - The processor vulnerability status is unknown because it is
+ out of Servicing period. Mitigation is not attempted.
+
+Definitions:
+------------
+
+Servicing period: The process of providing functional and security updates to
+Intel processors or platforms, utilizing the Intel Platform Update (IPU)
+process or other similar mechanisms.
+
+End of Servicing Updates (ESU): ESU is the date at which Intel will no
+longer provide Servicing, such as through IPU or other similar update
+processes. ESU dates will typically be aligned to end of quarter.
+
+If the processor is vulnerable then the following information is appended to
+the above information:
+
+ ======================== ===========================================
+ 'SMT vulnerable' SMT is enabled
+ 'SMT disabled' SMT is disabled
+ 'SMT Host state unknown' Kernel runs in a VM, Host SMT state unknown
+ ======================== ===========================================
+
+References
+----------
+.. [#f1] Affected Processors
+ https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html
diff --git a/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst b/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst
new file mode 100644
index 000000000..3b1ce68d2
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst
@@ -0,0 +1,149 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+SRBDS - Special Register Buffer Data Sampling
+=============================================
+
+SRBDS is a hardware vulnerability that allows MDS :doc:`mds` techniques to
+infer values returned from special register accesses. Special register
+accesses are accesses to off core registers. According to Intel's evaluation,
+the special register reads that have a security expectation of privacy are
+RDRAND, RDSEED and SGX EGETKEY.
+
+When RDRAND, RDSEED and EGETKEY instructions are used, the data is moved
+to the core through the special register mechanism that is susceptible
+to MDS attacks.
+
+Affected processors
+-------------------
+Core models (desktop, mobile, Xeon-E3) that implement RDRAND and/or RDSEED may
+be affected.
+
+A processor is affected by SRBDS if its Family_Model and stepping is
+in the following list, with the exception of the listed processors
+exporting MDS_NO while Intel TSX is available yet not enabled. The
+latter class of processors are only affected when Intel TSX is enabled
+by software using TSX_CTRL_MSR otherwise they are not affected.
+
+ ============= ============ ========
+ common name Family_Model Stepping
+ ============= ============ ========
+ IvyBridge 06_3AH All
+
+ Haswell 06_3CH All
+ Haswell_L 06_45H All
+ Haswell_G 06_46H All
+
+ Broadwell_G 06_47H All
+ Broadwell 06_3DH All
+
+ Skylake_L 06_4EH All
+ Skylake 06_5EH All
+
+ Kabylake_L 06_8EH <= 0xC
+ Kabylake 06_9EH <= 0xD
+ ============= ============ ========
+
+Related CVEs
+------------
+
+The following CVE entry is related to this SRBDS issue:
+
+ ============== ===== =====================================
+ CVE-2020-0543 SRBDS Special Register Buffer Data Sampling
+ ============== ===== =====================================
+
+Attack scenarios
+----------------
+An unprivileged user can extract values returned from RDRAND and RDSEED
+executed on another core or sibling thread using MDS techniques.
+
+
+Mitigation mechanism
+--------------------
+Intel will release microcode updates that modify the RDRAND, RDSEED, and
+EGETKEY instructions to overwrite secret special register data in the shared
+staging buffer before the secret data can be accessed by another logical
+processor.
+
+During execution of the RDRAND, RDSEED, or EGETKEY instructions, off-core
+accesses from other logical processors will be delayed until the special
+register read is complete and the secret data in the shared staging buffer is
+overwritten.
+
+This has three effects on performance:
+
+#. RDRAND, RDSEED, or EGETKEY instructions have higher latency.
+
+#. Executing RDRAND at the same time on multiple logical processors will be
+ serialized, resulting in an overall reduction in the maximum RDRAND
+ bandwidth.
+
+#. Executing RDRAND, RDSEED or EGETKEY will delay memory accesses from other
+ logical processors that miss their core caches, with an impact similar to
+ legacy locked cache-line-split accesses.
+
+The microcode updates provide an opt-out mechanism (RNGDS_MITG_DIS) to disable
+the mitigation for RDRAND and RDSEED instructions executed outside of Intel
+Software Guard Extensions (Intel SGX) enclaves. On logical processors that
+disable the mitigation using this opt-out mechanism, RDRAND and RDSEED do not
+take longer to execute and do not impact performance of sibling logical
+processors memory accesses. The opt-out mechanism does not affect Intel SGX
+enclaves (including execution of RDRAND or RDSEED inside an enclave, as well
+as EGETKEY execution).
+
+IA32_MCU_OPT_CTRL MSR Definition
+--------------------------------
+Along with the mitigation for this issue, Intel added a new thread-scope
+IA32_MCU_OPT_CTRL MSR, (address 0x123). The presence of this MSR and
+RNGDS_MITG_DIS (bit 0) is enumerated by CPUID.(EAX=07H,ECX=0).EDX[SRBDS_CTRL =
+9]==1. This MSR is introduced through the microcode update.
+
+Setting IA32_MCU_OPT_CTRL[0] (RNGDS_MITG_DIS) to 1 for a logical processor
+disables the mitigation for RDRAND and RDSEED executed outside of an Intel SGX
+enclave on that logical processor. Opting out of the mitigation for a
+particular logical processor does not affect the RDRAND and RDSEED mitigations
+for other logical processors.
+
+Note that inside of an Intel SGX enclave, the mitigation is applied regardless
+of the value of RNGDS_MITG_DS.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The kernel command line allows control over the SRBDS mitigation at boot time
+with the option "srbds=". The option for this is:
+
+ ============= =============================================================
+ off This option disables SRBDS mitigation for RDRAND and RDSEED on
+ affected platforms.
+ ============= =============================================================
+
+SRBDS System Information
+------------------------
+The Linux kernel provides vulnerability status information through sysfs. For
+SRBDS this can be accessed by the following sysfs file:
+/sys/devices/system/cpu/vulnerabilities/srbds
+
+The possible values contained in this file are:
+
+ ============================== =============================================
+ Not affected Processor not vulnerable
+ Vulnerable Processor vulnerable and mitigation disabled
+ Vulnerable: No microcode Processor vulnerable and microcode is missing
+ mitigation
+ Mitigation: Microcode Processor is vulnerable and mitigation is in
+ effect.
+ Mitigation: TSX disabled Processor is only vulnerable when TSX is
+ enabled while this system was booted with TSX
+ disabled.
+ Unknown: Dependent on
+ hypervisor status Running on virtual guest processor that is
+ affected but with no way to know if host
+ processor is mitigated or vulnerable.
+ ============================== =============================================
+
+SRBDS Default mitigation
+------------------------
+This new microcode serializes processor access during execution of RDRAND,
+RDSEED ensures that the shared buffer is overwritten before it is released for
+reuse. Use the "srbds=off" kernel command line to disable the mitigation for
+RDRAND and RDSEED.
diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
new file mode 100644
index 000000000..0fba3758d
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -0,0 +1,804 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Spectre Side Channels
+=====================
+
+Spectre is a class of side channel attacks that exploit branch prediction
+and speculative execution on modern CPUs to read memory, possibly
+bypassing access controls. Speculative execution side channel exploits
+do not modify memory but attempt to infer privileged data in the memory.
+
+This document covers Spectre variant 1 and Spectre variant 2.
+
+Affected processors
+-------------------
+
+Speculative execution side channel methods affect a wide range of modern
+high performance processors, since most modern high speed processors
+use branch prediction and speculative execution.
+
+The following CPUs are vulnerable:
+
+ - Intel Core, Atom, Pentium, and Xeon processors
+
+ - AMD Phenom, EPYC, and Zen processors
+
+ - IBM POWER and zSeries processors
+
+ - Higher end ARM processors
+
+ - Apple CPUs
+
+ - Higher end MIPS CPUs
+
+ - Likely most other high performance CPUs. Contact your CPU vendor for details.
+
+Whether a processor is affected or not can be read out from the Spectre
+vulnerability files in sysfs. See :ref:`spectre_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entries describe Spectre variants:
+
+ ============= ======================= ==========================
+ CVE-2017-5753 Bounds check bypass Spectre variant 1
+ CVE-2017-5715 Branch target injection Spectre variant 2
+ CVE-2019-1125 Spectre v1 swapgs Spectre variant 1 (swapgs)
+ ============= ======================= ==========================
+
+Problem
+-------
+
+CPUs use speculative operations to improve performance. That may leave
+traces of memory accesses or computations in the processor's caches,
+buffers, and branch predictors. Malicious software may be able to
+influence the speculative execution paths, and then use the side effects
+of the speculative execution in the CPUs' caches and buffers to infer
+privileged data touched during the speculative execution.
+
+Spectre variant 1 attacks take advantage of speculative execution of
+conditional branches, while Spectre variant 2 attacks use speculative
+execution of indirect branches to leak privileged memory.
+See :ref:`[1] <spec_ref1>` :ref:`[5] <spec_ref5>` :ref:`[6] <spec_ref6>`
+:ref:`[7] <spec_ref7>` :ref:`[10] <spec_ref10>` :ref:`[11] <spec_ref11>`.
+
+Spectre variant 1 (Bounds Check Bypass)
+---------------------------------------
+
+The bounds check bypass attack :ref:`[2] <spec_ref2>` takes advantage
+of speculative execution that bypasses conditional branch instructions
+used for memory access bounds check (e.g. checking if the index of an
+array results in memory access within a valid range). This results in
+memory accesses to invalid memory (with out-of-bound index) that are
+done speculatively before validation checks resolve. Such speculative
+memory accesses can leave side effects, creating side channels which
+leak information to the attacker.
+
+There are some extensions of Spectre variant 1 attacks for reading data
+over the network, see :ref:`[12] <spec_ref12>`. However such attacks
+are difficult, low bandwidth, fragile, and are considered low risk.
+
+Note that, despite "Bounds Check Bypass" name, Spectre variant 1 is not
+only about user-controlled array bounds checks. It can affect any
+conditional checks. The kernel entry code interrupt, exception, and NMI
+handlers all have conditional swapgs checks. Those may be problematic
+in the context of Spectre v1, as kernel code can speculatively run with
+a user GS.
+
+Spectre variant 2 (Branch Target Injection)
+-------------------------------------------
+
+The branch target injection attack takes advantage of speculative
+execution of indirect branches :ref:`[3] <spec_ref3>`. The indirect
+branch predictors inside the processor used to guess the target of
+indirect branches can be influenced by an attacker, causing gadget code
+to be speculatively executed, thus exposing sensitive data touched by
+the victim. The side effects left in the CPU's caches during speculative
+execution can be measured to infer data values.
+
+.. _poison_btb:
+
+In Spectre variant 2 attacks, the attacker can steer speculative indirect
+branches in the victim to gadget code by poisoning the branch target
+buffer of a CPU used for predicting indirect branch addresses. Such
+poisoning could be done by indirect branching into existing code,
+with the address offset of the indirect branch under the attacker's
+control. Since the branch prediction on impacted hardware does not
+fully disambiguate branch address and uses the offset for prediction,
+this could cause privileged code's indirect branch to jump to a gadget
+code with the same offset.
+
+The most useful gadgets take an attacker-controlled input parameter (such
+as a register value) so that the memory read can be controlled. Gadgets
+without input parameters might be possible, but the attacker would have
+very little control over what memory can be read, reducing the risk of
+the attack revealing useful data.
+
+One other variant 2 attack vector is for the attacker to poison the
+return stack buffer (RSB) :ref:`[13] <spec_ref13>` to cause speculative
+subroutine return instruction execution to go to a gadget. An attacker's
+imbalanced subroutine call instructions might "poison" entries in the
+return stack buffer which are later consumed by a victim's subroutine
+return instructions. This attack can be mitigated by flushing the return
+stack buffer on context switch, or virtual machine (VM) exit.
+
+On systems with simultaneous multi-threading (SMT), attacks are possible
+from the sibling thread, as level 1 cache and branch target buffer
+(BTB) may be shared between hardware threads in a CPU core. A malicious
+program running on the sibling thread may influence its peer's BTB to
+steer its indirect branch speculations to gadget code, and measure the
+speculative execution's side effects left in level 1 cache to infer the
+victim's data.
+
+Yet another variant 2 attack vector is for the attacker to poison the
+Branch History Buffer (BHB) to speculatively steer an indirect branch
+to a specific Branch Target Buffer (BTB) entry, even if the entry isn't
+associated with the source address of the indirect branch. Specifically,
+the BHB might be shared across privilege levels even in the presence of
+Enhanced IBRS.
+
+Currently the only known real-world BHB attack vector is via
+unprivileged eBPF. Therefore, it's highly recommended to not enable
+unprivileged eBPF, especially when eIBRS is used (without retpolines).
+For a full mitigation against BHB attacks, it's recommended to use
+retpolines (or eIBRS combined with retpolines).
+
+Attack scenarios
+----------------
+
+The following list of attack scenarios have been anticipated, but may
+not cover all possible attack vectors.
+
+1. A user process attacking the kernel
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Spectre variant 1
+~~~~~~~~~~~~~~~~~
+
+ The attacker passes a parameter to the kernel via a register or
+ via a known address in memory during a syscall. Such parameter may
+ be used later by the kernel as an index to an array or to derive
+ a pointer for a Spectre variant 1 attack. The index or pointer
+ is invalid, but bound checks are bypassed in the code branch taken
+ for speculative execution. This could cause privileged memory to be
+ accessed and leaked.
+
+ For kernel code that has been identified where data pointers could
+ potentially be influenced for Spectre attacks, new "nospec" accessor
+ macros are used to prevent speculative loading of data.
+
+Spectre variant 1 (swapgs)
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+ An attacker can train the branch predictor to speculatively skip the
+ swapgs path for an interrupt or exception. If they initialize
+ the GS register to a user-space value, if the swapgs is speculatively
+ skipped, subsequent GS-related percpu accesses in the speculation
+ window will be done with the attacker-controlled GS value. This
+ could cause privileged memory to be accessed and leaked.
+
+ For example:
+
+ ::
+
+ if (coming from user space)
+ swapgs
+ mov %gs:<percpu_offset>, %reg
+ mov (%reg), %reg1
+
+ When coming from user space, the CPU can speculatively skip the
+ swapgs, and then do a speculative percpu load using the user GS
+ value. So the user can speculatively force a read of any kernel
+ value. If a gadget exists which uses the percpu value as an address
+ in another load/store, then the contents of the kernel value may
+ become visible via an L1 side channel attack.
+
+ A similar attack exists when coming from kernel space. The CPU can
+ speculatively do the swapgs, causing the user GS to get used for the
+ rest of the speculative window.
+
+Spectre variant 2
+~~~~~~~~~~~~~~~~~
+
+ A spectre variant 2 attacker can :ref:`poison <poison_btb>` the branch
+ target buffer (BTB) before issuing syscall to launch an attack.
+ After entering the kernel, the kernel could use the poisoned branch
+ target buffer on indirect jump and jump to gadget code in speculative
+ execution.
+
+ If an attacker tries to control the memory addresses leaked during
+ speculative execution, he would also need to pass a parameter to the
+ gadget, either through a register or a known address in memory. After
+ the gadget has executed, he can measure the side effect.
+
+ The kernel can protect itself against consuming poisoned branch
+ target buffer entries by using return trampolines (also known as
+ "retpoline") :ref:`[3] <spec_ref3>` :ref:`[9] <spec_ref9>` for all
+ indirect branches. Return trampolines trap speculative execution paths
+ to prevent jumping to gadget code during speculative execution.
+ x86 CPUs with Enhanced Indirect Branch Restricted Speculation
+ (Enhanced IBRS) available in hardware should use the feature to
+ mitigate Spectre variant 2 instead of retpoline. Enhanced IBRS is
+ more efficient than retpoline.
+
+ There may be gadget code in firmware which could be exploited with
+ Spectre variant 2 attack by a rogue user process. To mitigate such
+ attacks on x86, Indirect Branch Restricted Speculation (IBRS) feature
+ is turned on before the kernel invokes any firmware code.
+
+2. A user process attacking another user process
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ A malicious user process can try to attack another user process,
+ either via a context switch on the same hardware thread, or from the
+ sibling hyperthread sharing a physical processor core on simultaneous
+ multi-threading (SMT) system.
+
+ Spectre variant 1 attacks generally require passing parameters
+ between the processes, which needs a data passing relationship, such
+ as remote procedure calls (RPC). Those parameters are used in gadget
+ code to derive invalid data pointers accessing privileged memory in
+ the attacked process.
+
+ Spectre variant 2 attacks can be launched from a rogue process by
+ :ref:`poisoning <poison_btb>` the branch target buffer. This can
+ influence the indirect branch targets for a victim process that either
+ runs later on the same hardware thread, or running concurrently on
+ a sibling hardware thread sharing the same physical core.
+
+ A user process can protect itself against Spectre variant 2 attacks
+ by using the prctl() syscall to disable indirect branch speculation
+ for itself. An administrator can also cordon off an unsafe process
+ from polluting the branch target buffer by disabling the process's
+ indirect branch speculation. This comes with a performance cost
+ from not using indirect branch speculation and clearing the branch
+ target buffer. When SMT is enabled on x86, for a process that has
+ indirect branch speculation disabled, Single Threaded Indirect Branch
+ Predictors (STIBP) :ref:`[4] <spec_ref4>` are turned on to prevent the
+ sibling thread from controlling branch target buffer. In addition,
+ the Indirect Branch Prediction Barrier (IBPB) is issued to clear the
+ branch target buffer when context switching to and from such process.
+
+ On x86, the return stack buffer is stuffed on context switch.
+ This prevents the branch target buffer from being used for branch
+ prediction when the return stack buffer underflows while switching to
+ a deeper call stack. Any poisoned entries in the return stack buffer
+ left by the previous process will also be cleared.
+
+ User programs should use address space randomization to make attacks
+ more difficult (Set /proc/sys/kernel/randomize_va_space = 1 or 2).
+
+3. A virtualized guest attacking the host
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ The attack mechanism is similar to how user processes attack the
+ kernel. The kernel is entered via hyper-calls or other virtualization
+ exit paths.
+
+ For Spectre variant 1 attacks, rogue guests can pass parameters
+ (e.g. in registers) via hyper-calls to derive invalid pointers to
+ speculate into privileged memory after entering the kernel. For places
+ where such kernel code has been identified, nospec accessor macros
+ are used to stop speculative memory access.
+
+ For Spectre variant 2 attacks, rogue guests can :ref:`poison
+ <poison_btb>` the branch target buffer or return stack buffer, causing
+ the kernel to jump to gadget code in the speculative execution paths.
+
+ To mitigate variant 2, the host kernel can use return trampolines
+ for indirect branches to bypass the poisoned branch target buffer,
+ and flushing the return stack buffer on VM exit. This prevents rogue
+ guests from affecting indirect branching in the host kernel.
+
+ To protect host processes from rogue guests, host processes can have
+ indirect branch speculation disabled via prctl(). The branch target
+ buffer is cleared before context switching to such processes.
+
+4. A virtualized guest attacking other guest
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ A rogue guest may attack another guest to get data accessible by the
+ other guest.
+
+ Spectre variant 1 attacks are possible if parameters can be passed
+ between guests. This may be done via mechanisms such as shared memory
+ or message passing. Such parameters could be used to derive data
+ pointers to privileged data in guest. The privileged data could be
+ accessed by gadget code in the victim's speculation paths.
+
+ Spectre variant 2 attacks can be launched from a rogue guest by
+ :ref:`poisoning <poison_btb>` the branch target buffer or the return
+ stack buffer. Such poisoned entries could be used to influence
+ speculation execution paths in the victim guest.
+
+ Linux kernel mitigates attacks to other guests running in the same
+ CPU hardware thread by flushing the return stack buffer on VM exit,
+ and clearing the branch target buffer before switching to a new guest.
+
+ If SMT is used, Spectre variant 2 attacks from an untrusted guest
+ in the sibling hyperthread can be mitigated by the administrator,
+ by turning off the unsafe guest's indirect branch speculation via
+ prctl(). A guest can also protect itself by turning on microcode
+ based mitigations (such as IBPB or STIBP on x86) within the guest.
+
+.. _spectre_sys_info:
+
+Spectre system information
+--------------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current
+mitigation status of the system for Spectre: whether the system is
+vulnerable, and which mitigations are active.
+
+The sysfs file showing Spectre variant 1 mitigation status is:
+
+ /sys/devices/system/cpu/vulnerabilities/spectre_v1
+
+The possible values in this file are:
+
+ .. list-table::
+
+ * - 'Not affected'
+ - The processor is not vulnerable.
+ * - 'Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers'
+ - The swapgs protections are disabled; otherwise it has
+ protection in the kernel on a case by case base with explicit
+ pointer sanitation and usercopy LFENCE barriers.
+ * - 'Mitigation: usercopy/swapgs barriers and __user pointer sanitization'
+ - Protection in the kernel on a case by case base with explicit
+ pointer sanitation, usercopy LFENCE barriers, and swapgs LFENCE
+ barriers.
+
+However, the protections are put in place on a case by case basis,
+and there is no guarantee that all possible attack vectors for Spectre
+variant 1 are covered.
+
+The spectre_v2 kernel file reports if the kernel has been compiled with
+retpoline mitigation or if the CPU has hardware mitigation, and if the
+CPU has support for additional process-specific mitigation.
+
+This file also reports CPU features enabled by microcode to mitigate
+attack between user processes:
+
+1. Indirect Branch Prediction Barrier (IBPB) to add additional
+ isolation between processes of different users.
+2. Single Thread Indirect Branch Predictors (STIBP) to add additional
+ isolation between CPU threads running on the same core.
+
+These CPU features may impact performance when used and can be enabled
+per process on a case-by-case base.
+
+The sysfs file showing Spectre variant 2 mitigation status is:
+
+ /sys/devices/system/cpu/vulnerabilities/spectre_v2
+
+The possible values in this file are:
+
+ - Kernel status:
+
+ ======================================== =================================
+ 'Not affected' The processor is not vulnerable
+ 'Mitigation: None' Vulnerable, no mitigation
+ 'Mitigation: Retpolines' Use Retpoline thunks
+ 'Mitigation: LFENCE' Use LFENCE instructions
+ 'Mitigation: Enhanced IBRS' Hardware-focused mitigation
+ 'Mitigation: Enhanced IBRS + Retpolines' Hardware-focused + Retpolines
+ 'Mitigation: Enhanced IBRS + LFENCE' Hardware-focused + LFENCE
+ ======================================== =================================
+
+ - Firmware status: Show if Indirect Branch Restricted Speculation (IBRS) is
+ used to protect against Spectre variant 2 attacks when calling firmware (x86 only).
+
+ ========== =============================================================
+ 'IBRS_FW' Protection against user program attacks when calling firmware
+ ========== =============================================================
+
+ - Indirect branch prediction barrier (IBPB) status for protection between
+ processes of different users. This feature can be controlled through
+ prctl() per process, or through kernel command line options. This is
+ an x86 only feature. For more details see below.
+
+ =================== ========================================================
+ 'IBPB: disabled' IBPB unused
+ 'IBPB: always-on' Use IBPB on all tasks
+ 'IBPB: conditional' Use IBPB on SECCOMP or indirect branch restricted tasks
+ =================== ========================================================
+
+ - Single threaded indirect branch prediction (STIBP) status for protection
+ between different hyper threads. This feature can be controlled through
+ prctl per process, or through kernel command line options. This is x86
+ only feature. For more details see below.
+
+ ==================== ========================================================
+ 'STIBP: disabled' STIBP unused
+ 'STIBP: forced' Use STIBP on all tasks
+ 'STIBP: conditional' Use STIBP on SECCOMP or indirect branch restricted tasks
+ ==================== ========================================================
+
+ - Return stack buffer (RSB) protection status:
+
+ ============= ===========================================
+ 'RSB filling' Protection of RSB on context switch enabled
+ ============= ===========================================
+
+ - EIBRS Post-barrier Return Stack Buffer (PBRSB) protection status:
+
+ =========================== =======================================================
+ 'PBRSB-eIBRS: SW sequence' CPU is affected and protection of RSB on VMEXIT enabled
+ 'PBRSB-eIBRS: Vulnerable' CPU is vulnerable
+ 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB
+ =========================== =======================================================
+
+Full mitigation might require a microcode update from the CPU
+vendor. When the necessary microcode is not available, the kernel will
+report vulnerability.
+
+Turning on mitigation for Spectre variant 1 and Spectre variant 2
+-----------------------------------------------------------------
+
+1. Kernel mitigation
+^^^^^^^^^^^^^^^^^^^^
+
+Spectre variant 1
+~~~~~~~~~~~~~~~~~
+
+ For the Spectre variant 1, vulnerable kernel code (as determined
+ by code audit or scanning tools) is annotated on a case by case
+ basis to use nospec accessor macros for bounds clipping :ref:`[2]
+ <spec_ref2>` to avoid any usable disclosure gadgets. However, it may
+ not cover all attack vectors for Spectre variant 1.
+
+ Copy-from-user code has an LFENCE barrier to prevent the access_ok()
+ check from being mis-speculated. The barrier is done by the
+ barrier_nospec() macro.
+
+ For the swapgs variant of Spectre variant 1, LFENCE barriers are
+ added to interrupt, exception and NMI entry where needed. These
+ barriers are done by the FENCE_SWAPGS_KERNEL_ENTRY and
+ FENCE_SWAPGS_USER_ENTRY macros.
+
+Spectre variant 2
+~~~~~~~~~~~~~~~~~
+
+ For Spectre variant 2 mitigation, the compiler turns indirect calls or
+ jumps in the kernel into equivalent return trampolines (retpolines)
+ :ref:`[3] <spec_ref3>` :ref:`[9] <spec_ref9>` to go to the target
+ addresses. Speculative execution paths under retpolines are trapped
+ in an infinite loop to prevent any speculative execution jumping to
+ a gadget.
+
+ To turn on retpoline mitigation on a vulnerable CPU, the kernel
+ needs to be compiled with a gcc compiler that supports the
+ -mindirect-branch=thunk-extern -mindirect-branch-register options.
+ If the kernel is compiled with a Clang compiler, the compiler needs
+ to support -mretpoline-external-thunk option. The kernel config
+ CONFIG_RETPOLINE needs to be turned on, and the CPU needs to run with
+ the latest updated microcode.
+
+ On Intel Skylake-era systems the mitigation covers most, but not all,
+ cases. See :ref:`[3] <spec_ref3>` for more details.
+
+ On CPUs with hardware mitigation for Spectre variant 2 (e.g. IBRS
+ or enhanced IBRS on x86), retpoline is automatically disabled at run time.
+
+ Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
+ boot, by setting the IBRS bit, and they're automatically protected against
+ Spectre v2 variant attacks, including cross-thread branch target injections
+ on SMT systems (STIBP). In other words, eIBRS enables STIBP too.
+
+ Legacy IBRS systems clear the IBRS bit on exit to userspace and
+ therefore explicitly enable STIBP for that
+
+ The retpoline mitigation is turned on by default on vulnerable
+ CPUs. It can be forced on or off by the administrator
+ via the kernel command line and sysfs control files. See
+ :ref:`spectre_mitigation_control_command_line`.
+
+ On x86, indirect branch restricted speculation is turned on by default
+ before invoking any firmware code to prevent Spectre variant 2 exploits
+ using the firmware.
+
+ Using kernel address space randomization (CONFIG_RANDOMIZE_BASE=y
+ and CONFIG_SLAB_FREELIST_RANDOM=y in the kernel configuration) makes
+ attacks on the kernel generally more difficult.
+
+2. User program mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ User programs can mitigate Spectre variant 1 using LFENCE or "bounds
+ clipping". For more details see :ref:`[2] <spec_ref2>`.
+
+ For Spectre variant 2 mitigation, individual user programs
+ can be compiled with return trampolines for indirect branches.
+ This protects them from consuming poisoned entries in the branch
+ target buffer left by malicious software.
+
+ On legacy IBRS systems, at return to userspace, implicit STIBP is disabled
+ because the kernel clears the IBRS bit. In this case, the userspace programs
+ can disable indirect branch speculation via prctl() (See
+ :ref:`Documentation/userspace-api/spec_ctrl.rst <set_spec_ctrl>`).
+ On x86, this will turn on STIBP to guard against attacks from the
+ sibling thread when the user program is running, and use IBPB to
+ flush the branch target buffer when switching to/from the program.
+
+ Restricting indirect branch speculation on a user program will
+ also prevent the program from launching a variant 2 attack
+ on x86. All sand-boxed SECCOMP programs have indirect branch
+ speculation restricted by default. Administrators can change
+ that behavior via the kernel command line and sysfs control files.
+ See :ref:`spectre_mitigation_control_command_line`.
+
+ Programs that disable their indirect branch speculation will have
+ more overhead and run slower.
+
+ User programs should use address space randomization
+ (/proc/sys/kernel/randomize_va_space = 1 or 2) to make attacks more
+ difficult.
+
+3. VM mitigation
+^^^^^^^^^^^^^^^^
+
+ Within the kernel, Spectre variant 1 attacks from rogue guests are
+ mitigated on a case by case basis in VM exit paths. Vulnerable code
+ uses nospec accessor macros for "bounds clipping", to avoid any
+ usable disclosure gadgets. However, this may not cover all variant
+ 1 attack vectors.
+
+ For Spectre variant 2 attacks from rogue guests to the kernel, the
+ Linux kernel uses retpoline or Enhanced IBRS to prevent consumption of
+ poisoned entries in branch target buffer left by rogue guests. It also
+ flushes the return stack buffer on every VM exit to prevent a return
+ stack buffer underflow so poisoned branch target buffer could be used,
+ or attacker guests leaving poisoned entries in the return stack buffer.
+
+ To mitigate guest-to-guest attacks in the same CPU hardware thread,
+ the branch target buffer is sanitized by flushing before switching
+ to a new guest on a CPU.
+
+ The above mitigations are turned on by default on vulnerable CPUs.
+
+ To mitigate guest-to-guest attacks from sibling thread when SMT is
+ in use, an untrusted guest running in the sibling thread can have
+ its indirect branch speculation disabled by administrator via prctl().
+
+ The kernel also allows guests to use any microcode based mitigation
+ they choose to use (such as IBPB or STIBP on x86) to protect themselves.
+
+.. _spectre_mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+Spectre variant 2 mitigation can be disabled or force enabled at the
+kernel command line.
+
+ nospectre_v1
+
+ [X86,PPC] Disable mitigations for Spectre Variant 1
+ (bounds check bypass). With this option data leaks are
+ possible in the system.
+
+ nospectre_v2
+
+ [X86] Disable all mitigations for the Spectre variant 2
+ (indirect branch prediction) vulnerability. System may
+ allow data leaks with this option, which is equivalent
+ to spectre_v2=off.
+
+
+ spectre_v2=
+
+ [X86] Control mitigation of Spectre variant 2
+ (indirect branch speculation) vulnerability.
+ The default operation protects the kernel from
+ user space attacks.
+
+ on
+ unconditionally enable, implies
+ spectre_v2_user=on
+ off
+ unconditionally disable, implies
+ spectre_v2_user=off
+ auto
+ kernel detects whether your CPU model is
+ vulnerable
+
+ Selecting 'on' will, and 'auto' may, choose a
+ mitigation method at run time according to the
+ CPU, the available microcode, the setting of the
+ CONFIG_RETPOLINE configuration option, and the
+ compiler with which the kernel was built.
+
+ Selecting 'on' will also enable the mitigation
+ against user space to user space task attacks.
+
+ Selecting 'off' will disable both the kernel and
+ the user space protections.
+
+ Specific mitigations can also be selected manually:
+
+ retpoline auto pick between generic,lfence
+ retpoline,generic Retpolines
+ retpoline,lfence LFENCE; indirect branch
+ retpoline,amd alias for retpoline,lfence
+ eibrs enhanced IBRS
+ eibrs,retpoline enhanced IBRS + Retpolines
+ eibrs,lfence enhanced IBRS + LFENCE
+
+ Not specifying this option is equivalent to
+ spectre_v2=auto.
+
+For user space mitigation:
+
+ spectre_v2_user=
+
+ [X86] Control mitigation of Spectre variant 2
+ (indirect branch speculation) vulnerability between
+ user space tasks
+
+ on
+ Unconditionally enable mitigations. Is
+ enforced by spectre_v2=on
+
+ off
+ Unconditionally disable mitigations. Is
+ enforced by spectre_v2=off
+
+ prctl
+ Indirect branch speculation is enabled,
+ but mitigation can be enabled via prctl
+ per thread. The mitigation control state
+ is inherited on fork.
+
+ prctl,ibpb
+ Like "prctl" above, but only STIBP is
+ controlled per thread. IBPB is issued
+ always when switching between different user
+ space processes.
+
+ seccomp
+ Same as "prctl" above, but all seccomp
+ threads will enable the mitigation unless
+ they explicitly opt out.
+
+ seccomp,ibpb
+ Like "seccomp" above, but only STIBP is
+ controlled per thread. IBPB is issued
+ always when switching between different
+ user space processes.
+
+ auto
+ Kernel selects the mitigation depending on
+ the available CPU features and vulnerability.
+
+ Default mitigation:
+ If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl"
+
+ Not specifying this option is equivalent to
+ spectre_v2_user=auto.
+
+ In general the kernel by default selects
+ reasonable mitigations for the current CPU. To
+ disable Spectre variant 2 mitigations, boot with
+ spectre_v2=off. Spectre variant 1 mitigations
+ cannot be disabled.
+
+Mitigation selection guide
+--------------------------
+
+1. Trusted userspace
+^^^^^^^^^^^^^^^^^^^^
+
+ If all userspace applications are from trusted sources and do not
+ execute externally supplied untrusted code, then the mitigations can
+ be disabled.
+
+2. Protect sensitive programs
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ For security-sensitive programs that have secrets (e.g. crypto
+ keys), protection against Spectre variant 2 can be put in place by
+ disabling indirect branch speculation when the program is running
+ (See :ref:`Documentation/userspace-api/spec_ctrl.rst <set_spec_ctrl>`).
+
+3. Sandbox untrusted programs
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ Untrusted programs that could be a source of attacks can be cordoned
+ off by disabling their indirect branch speculation when they are run
+ (See :ref:`Documentation/userspace-api/spec_ctrl.rst <set_spec_ctrl>`).
+ This prevents untrusted programs from polluting the branch target
+ buffer. All programs running in SECCOMP sandboxes have indirect
+ branch speculation restricted by default. This behavior can be
+ changed via the kernel command line and sysfs control files. See
+ :ref:`spectre_mitigation_control_command_line`.
+
+3. High security mode
+^^^^^^^^^^^^^^^^^^^^^
+
+ All Spectre variant 2 mitigations can be forced on
+ at boot time for all programs (See the "on" option in
+ :ref:`spectre_mitigation_control_command_line`). This will add
+ overhead as indirect branch speculations for all programs will be
+ restricted.
+
+ On x86, branch target buffer will be flushed with IBPB when switching
+ to a new program. STIBP is left on all the time to protect programs
+ against variant 2 attacks originating from programs running on
+ sibling threads.
+
+ Alternatively, STIBP can be used only when running programs
+ whose indirect branch speculation is explicitly disabled,
+ while IBPB is still used all the time when switching to a new
+ program to clear the branch target buffer (See "ibpb" option in
+ :ref:`spectre_mitigation_control_command_line`). This "ibpb" option
+ has less performance cost than the "on" option, which leaves STIBP
+ on all the time.
+
+References on Spectre
+---------------------
+
+Intel white papers:
+
+.. _spec_ref1:
+
+[1] `Intel analysis of speculative execution side channels <https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/Intel-Analysis-of-Speculative-Execution-Side-Channels.pdf>`_.
+
+.. _spec_ref2:
+
+[2] `Bounds check bypass <https://software.intel.com/security-software-guidance/software-guidance/bounds-check-bypass>`_.
+
+.. _spec_ref3:
+
+[3] `Deep dive: Retpoline: A branch target injection mitigation <https://software.intel.com/security-software-guidance/insights/deep-dive-retpoline-branch-target-injection-mitigation>`_.
+
+.. _spec_ref4:
+
+[4] `Deep Dive: Single Thread Indirect Branch Predictors <https://software.intel.com/security-software-guidance/insights/deep-dive-single-thread-indirect-branch-predictors>`_.
+
+AMD white papers:
+
+.. _spec_ref5:
+
+[5] `AMD64 technology indirect branch control extension <https://developer.amd.com/wp-content/resources/Architecture_Guidelines_Update_Indirect_Branch_Control.pdf>`_.
+
+.. _spec_ref6:
+
+[6] `Software techniques for managing speculation on AMD processors <https://developer.amd.com/wp-content/resources/Managing-Speculation-on-AMD-Processors.pdf>`_.
+
+ARM white papers:
+
+.. _spec_ref7:
+
+[7] `Cache speculation side-channels <https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability/download-the-whitepaper>`_.
+
+.. _spec_ref8:
+
+[8] `Cache speculation issues update <https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability/latest-updates/cache-speculation-issues-update>`_.
+
+Google white paper:
+
+.. _spec_ref9:
+
+[9] `Retpoline: a software construct for preventing branch-target-injection <https://support.google.com/faqs/answer/7625886>`_.
+
+MIPS white paper:
+
+.. _spec_ref10:
+
+[10] `MIPS: response on speculative execution and side channel vulnerabilities <https://www.mips.com/blog/mips-response-on-speculative-execution-and-side-channel-vulnerabilities/>`_.
+
+Academic papers:
+
+.. _spec_ref11:
+
+[11] `Spectre Attacks: Exploiting Speculative Execution <https://spectreattack.com/spectre.pdf>`_.
+
+.. _spec_ref12:
+
+[12] `NetSpectre: Read Arbitrary Memory over Network <https://arxiv.org/abs/1807.10535>`_.
+
+.. _spec_ref13:
+
+[13] `Spectre Returns! Speculation Attacks using the Return Stack Buffer <https://www.usenix.org/system/files/conference/woot18/woot18-paper-koruyeh.pdf>`_.
diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst
new file mode 100644
index 000000000..f79cb11b0
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/srso.rst
@@ -0,0 +1,133 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Speculative Return Stack Overflow (SRSO)
+========================================
+
+This is a mitigation for the speculative return stack overflow (SRSO)
+vulnerability found on AMD processors. The mechanism is by now the well
+known scenario of poisoning CPU functional units - the Branch Target
+Buffer (BTB) and Return Address Predictor (RAP) in this case - and then
+tricking the elevated privilege domain (the kernel) into leaking
+sensitive data.
+
+AMD CPUs predict RET instructions using a Return Address Predictor (aka
+Return Address Stack/Return Stack Buffer). In some cases, a non-architectural
+CALL instruction (i.e., an instruction predicted to be a CALL but is
+not actually a CALL) can create an entry in the RAP which may be used
+to predict the target of a subsequent RET instruction.
+
+The specific circumstances that lead to this varies by microarchitecture
+but the concern is that an attacker can mis-train the CPU BTB to predict
+non-architectural CALL instructions in kernel space and use this to
+control the speculative target of a subsequent kernel RET, potentially
+leading to information disclosure via a speculative side-channel.
+
+The issue is tracked under CVE-2023-20569.
+
+Affected processors
+-------------------
+
+AMD Zen, generations 1-4. That is, all families 0x17 and 0x19. Older
+processors have not been investigated.
+
+System information and options
+------------------------------
+
+First of all, it is required that the latest microcode be loaded for
+mitigations to be effective.
+
+The sysfs file showing SRSO mitigation status is:
+
+ /sys/devices/system/cpu/vulnerabilities/spec_rstack_overflow
+
+The possible values in this file are:
+
+ - 'Not affected' The processor is not vulnerable
+
+ - 'Vulnerable: no microcode' The processor is vulnerable, no
+ microcode extending IBPB functionality
+ to address the vulnerability has been
+ applied.
+
+ - 'Mitigation: microcode' Extended IBPB functionality microcode
+ patch has been applied. It does not
+ address User->Kernel and Guest->Host
+ transitions protection but it does
+ address User->User and VM->VM attack
+ vectors.
+
+ (spec_rstack_overflow=microcode)
+
+ - 'Mitigation: safe RET' Software-only mitigation. It complements
+ the extended IBPB microcode patch
+ functionality by addressing User->Kernel
+ and Guest->Host transitions protection.
+
+ Selected by default or by
+ spec_rstack_overflow=safe-ret
+
+ - 'Mitigation: IBPB' Similar protection as "safe RET" above
+ but employs an IBPB barrier on privilege
+ domain crossings (User->Kernel,
+ Guest->Host).
+
+ (spec_rstack_overflow=ibpb)
+
+ - 'Mitigation: IBPB on VMEXIT' Mitigation addressing the cloud provider
+ scenario - the Guest->Host transitions
+ only.
+
+ (spec_rstack_overflow=ibpb-vmexit)
+
+In order to exploit vulnerability, an attacker needs to:
+
+ - gain local access on the machine
+
+ - break kASLR
+
+ - find gadgets in the running kernel in order to use them in the exploit
+
+ - potentially create and pin an additional workload on the sibling
+ thread, depending on the microarchitecture (not necessary on fam 0x19)
+
+ - run the exploit
+
+Considering the performance implications of each mitigation type, the
+default one is 'Mitigation: safe RET' which should take care of most
+attack vectors, including the local User->Kernel one.
+
+As always, the user is advised to keep her/his system up-to-date by
+applying software updates regularly.
+
+The default setting will be reevaluated when needed and especially when
+new attack vectors appear.
+
+As one can surmise, 'Mitigation: safe RET' does come at the cost of some
+performance depending on the workload. If one trusts her/his userspace
+and does not want to suffer the performance impact, one can always
+disable the mitigation with spec_rstack_overflow=off.
+
+Similarly, 'Mitigation: IBPB' is another full mitigation type employing
+an indrect branch prediction barrier after having applied the required
+microcode patch for one's system. This mitigation comes also at
+a performance cost.
+
+Mitigation: safe RET
+--------------------
+
+The mitigation works by ensuring all RET instructions speculate to
+a controlled location, similar to how speculation is controlled in the
+retpoline sequence. To accomplish this, the __x86_return_thunk forces
+the CPU to mispredict every function return using a 'safe return'
+sequence.
+
+To ensure the safety of this mitigation, the kernel must ensure that the
+safe return sequence is itself free from attacker interference. In Zen3
+and Zen4, this is accomplished by creating a BTB alias between the
+untraining function srso_alias_untrain_ret() and the safe return
+function srso_alias_safe_ret() which results in evicting a potentially
+poisoned BTB entry and using that safe one for all function returns.
+
+In older Zen1 and Zen2, this is accomplished using a reinterpretation
+technique similar to Retbleed one: srso_untrain_ret() and
+srso_safe_ret().
diff --git a/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
new file mode 100644
index 000000000..68d96f0e9
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
@@ -0,0 +1,277 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+TAA - TSX Asynchronous Abort
+======================================
+
+TAA is a hardware vulnerability that allows unprivileged speculative access to
+data which is available in various CPU internal buffers by using asynchronous
+aborts within an Intel TSX transactional region.
+
+Affected processors
+-------------------
+
+This vulnerability only affects Intel processors that support Intel
+Transactional Synchronization Extensions (TSX) when the TAA_NO bit (bit 8)
+is 0 in the IA32_ARCH_CAPABILITIES MSR. On processors where the MDS_NO bit
+(bit 5) is 0 in the IA32_ARCH_CAPABILITIES MSR, the existing MDS mitigations
+also mitigate against TAA.
+
+Whether a processor is affected or not can be read out from the TAA
+vulnerability file in sysfs. See :ref:`tsx_async_abort_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entry is related to this TAA issue:
+
+ ============== ===== ===================================================
+ CVE-2019-11135 TAA TSX Asynchronous Abort (TAA) condition on some
+ microprocessors utilizing speculative execution may
+ allow an authenticated user to potentially enable
+ information disclosure via a side channel with
+ local access.
+ ============== ===== ===================================================
+
+Problem
+-------
+
+When performing store, load or L1 refill operations, processors write
+data into temporary microarchitectural structures (buffers). The data in
+those buffers can be forwarded to load operations as an optimization.
+
+Intel TSX is an extension to the x86 instruction set architecture that adds
+hardware transactional memory support to improve performance of multi-threaded
+software. TSX lets the processor expose and exploit concurrency hidden in an
+application due to dynamically avoiding unnecessary synchronization.
+
+TSX supports atomic memory transactions that are either committed (success) or
+aborted. During an abort, operations that happened within the transactional region
+are rolled back. An asynchronous abort takes place, among other options, when a
+different thread accesses a cache line that is also used within the transactional
+region when that access might lead to a data race.
+
+Immediately after an uncompleted asynchronous abort, certain speculatively
+executed loads may read data from those internal buffers and pass it to dependent
+operations. This can be then used to infer the value via a cache side channel
+attack.
+
+Because the buffers are potentially shared between Hyper-Threads cross
+Hyper-Thread attacks are possible.
+
+The victim of a malicious actor does not need to make use of TSX. Only the
+attacker needs to begin a TSX transaction and raise an asynchronous abort
+which in turn potenitally leaks data stored in the buffers.
+
+More detailed technical information is available in the TAA specific x86
+architecture section: :ref:`Documentation/x86/tsx_async_abort.rst <tsx_async_abort>`.
+
+
+Attack scenarios
+----------------
+
+Attacks against the TAA vulnerability can be implemented from unprivileged
+applications running on hosts or guests.
+
+As for MDS, the attacker has no control over the memory addresses that can
+be leaked. Only the victim is responsible for bringing data to the CPU. As
+a result, the malicious actor has to sample as much data as possible and
+then postprocess it to try to infer any useful information from it.
+
+A potential attacker only has read access to the data. Also, there is no direct
+privilege escalation by using this technique.
+
+
+.. _tsx_async_abort_sys_info:
+
+TAA system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current TAA status
+of mitigated systems. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+
+The possible values in this file are:
+
+.. list-table::
+
+ * - 'Vulnerable'
+ - The CPU is affected by this vulnerability and the microcode and kernel mitigation are not applied.
+ * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+ - The system tries to clear the buffers but the microcode might not support the operation.
+ * - 'Mitigation: Clear CPU buffers'
+ - The microcode has been updated to clear the buffers. TSX is still enabled.
+ * - 'Mitigation: TSX disabled'
+ - TSX is disabled.
+ * - 'Not affected'
+ - The CPU is not affected by this issue.
+
+.. _ucode_needed:
+
+Best effort mitigation mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If the processor is vulnerable, but the availability of the microcode-based
+mitigation mechanism is not advertised via CPUID the kernel selects a best
+effort mitigation mode. This mode invokes the mitigation instructions
+without a guarantee that they clear the CPU buffers.
+
+This is done to address virtualization scenarios where the host has the
+microcode update applied, but the hypervisor is not yet updated to expose the
+CPUID to the guest. If the host has updated microcode the protection takes
+effect; otherwise a few CPU cycles are wasted pointlessly.
+
+The state in the tsx_async_abort sysfs file reflects this situation
+accordingly.
+
+
+Mitigation mechanism
+--------------------
+
+The kernel detects the affected CPUs and the presence of the microcode which is
+required. If a CPU is affected and the microcode is available, then the kernel
+enables the mitigation by default.
+
+
+The mitigation can be controlled at boot time via a kernel command line option.
+See :ref:`taa_mitigation_control_command_line`.
+
+Virtualization mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Affected systems where the host has TAA microcode and TAA is mitigated by
+having disabled TSX previously, are not vulnerable regardless of the status
+of the VMs.
+
+In all other cases, if the host either does not have the TAA microcode or
+the kernel is not mitigated, the system might be vulnerable.
+
+
+.. _taa_mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the TAA mitigations at boot time with
+the option "tsx_async_abort=". The valid arguments for this option are:
+
+ ============ =============================================================
+ off This option disables the TAA mitigation on affected platforms.
+ If the system has TSX enabled (see next parameter) and the CPU
+ is affected, the system is vulnerable.
+
+ full TAA mitigation is enabled. If TSX is enabled, on an affected
+ system it will clear CPU buffers on ring transitions. On
+ systems which are MDS-affected and deploy MDS mitigation,
+ TAA is also mitigated. Specifying this option on those
+ systems will have no effect.
+
+ full,nosmt The same as tsx_async_abort=full, with SMT disabled on
+ vulnerable CPUs that have TSX enabled. This is the complete
+ mitigation. When TSX is disabled, SMT is not disabled because
+ CPU is not vulnerable to cross-thread TAA attacks.
+ ============ =============================================================
+
+Not specifying this option is equivalent to "tsx_async_abort=full". For
+processors that are affected by both TAA and MDS, specifying just
+"tsx_async_abort=off" without an accompanying "mds=off" will have no
+effect as the same mitigation is used for both vulnerabilities.
+
+The kernel command line also allows to control the TSX feature using the
+parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used
+to control the TSX feature and the enumeration of the TSX feature bits (RTM
+and HLE) in CPUID.
+
+The valid options are:
+
+ ============ =============================================================
+ off Disables TSX on the system.
+
+ Note that this option takes effect only on newer CPUs which are
+ not vulnerable to MDS, i.e., have MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1
+ and which get the new IA32_TSX_CTRL MSR through a microcode
+ update. This new MSR allows for the reliable deactivation of
+ the TSX functionality.
+
+ on Enables TSX.
+
+ Although there are mitigations for all known security
+ vulnerabilities, TSX has been known to be an accelerator for
+ several previous speculation-related CVEs, and so there may be
+ unknown security risks associated with leaving it enabled.
+
+ auto Disables TSX if X86_BUG_TAA is present, otherwise enables TSX
+ on the system.
+ ============ =============================================================
+
+Not specifying this option is equivalent to "tsx=off".
+
+The following combinations of the "tsx_async_abort" and "tsx" are possible. For
+affected platforms tsx=auto is equivalent to tsx=off and the result will be:
+
+ ========= ========================== =========================================
+ tsx=on tsx_async_abort=full The system will use VERW to clear CPU
+ buffers. Cross-thread attacks are still
+ possible on SMT machines.
+ tsx=on tsx_async_abort=full,nosmt As above, cross-thread attacks on SMT
+ mitigated.
+ tsx=on tsx_async_abort=off The system is vulnerable.
+ tsx=off tsx_async_abort=full TSX might be disabled if microcode
+ provides a TSX control MSR. If so,
+ system is not vulnerable.
+ tsx=off tsx_async_abort=full,nosmt Ditto
+ tsx=off tsx_async_abort=off ditto
+ ========= ========================== =========================================
+
+
+For unaffected platforms "tsx=on" and "tsx_async_abort=full" does not clear CPU
+buffers. For platforms without TSX control (MSR_IA32_ARCH_CAPABILITIES.MDS_NO=0)
+"tsx" command line argument has no effect.
+
+For the affected platforms below table indicates the mitigation status for the
+combinations of CPUID bit MD_CLEAR and IA32_ARCH_CAPABILITIES MSR bits MDS_NO
+and TSX_CTRL_MSR.
+
+ ======= ========= ============= ========================================
+ MDS_NO MD_CLEAR TSX_CTRL_MSR Status
+ ======= ========= ============= ========================================
+ 0 0 0 Vulnerable (needs microcode)
+ 0 1 0 MDS and TAA mitigated via VERW
+ 1 1 0 MDS fixed, TAA vulnerable if TSX enabled
+ because MD_CLEAR has no meaning and
+ VERW is not guaranteed to clear buffers
+ 1 X 1 MDS fixed, TAA can be mitigated by
+ VERW or TSX_CTRL_MSR
+ ======= ========= ============= ========================================
+
+Mitigation selection guide
+--------------------------
+
+1. Trusted userspace and guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If all user space applications are from a trusted source and do not execute
+untrusted code which is supplied externally, then the mitigation can be
+disabled. The same applies to virtualized environments with trusted guests.
+
+
+2. Untrusted userspace and guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+If there are untrusted applications or guests on the system, enabling TSX
+might allow a malicious actor to leak data from the host or from other
+processes running on the same physical core.
+
+If the microcode is available and the TSX is disabled on the host, attacks
+are prevented in a virtualized environment as well, even if the VMs do not
+explicitly enable the mitigation.
+
+
+.. _taa_default_mitigations:
+
+Default mitigations
+-------------------
+
+The kernel's default action for vulnerable processors is:
+
+ - Deploy TSX disable mitigation (tsx_async_abort=full tsx=off).